{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:40:52Z","timestamp":1767141652161,"version":"build-2238731810"},"reference-count":166,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s11263-024-02343-w","type":"journal-article","created":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T12:32:48Z","timestamp":1740054768000},"page":"4014-4041","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Consistent Prompt Tuning for Generalized Category Discovery"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5959-2931","authenticated-orcid":false,"given":"Muli","family":"Yang","sequence":"first","affiliation":[]},{"given":"Jie","family":"Yin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6837-4605","authenticated-orcid":false,"given":"Yanan","family":"Gu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2620-3247","authenticated-orcid":false,"given":"Cheng","family":"Deng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-8739","authenticated-orcid":false,"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Hongyuan","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,20]]},"reference":[{"key":"2343_CR1","unstructured":"Alayrac, J.-B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et\u00a0al. (2022). Flamingo: a visual language model for few-shot learning. In Conference on neural information processing systems (NeurIPS), (pp. 23716\u201323736)"},{"key":"2343_CR2","doi-asserted-by":"crossref","unstructured":"An, W., Shi, W., Tian, F., Lin, H., Wang, Q., Wu, Y., Cai, M., Wang, L., Chen, Y., Zhu, H., et\u00a0al. (2023a). Generalized category discovery with large language models in the loop. arXiv preprint arXiv:2312.10897.","DOI":"10.18653\/v1\/2024.findings-acl.512"},{"key":"2343_CR3","doi-asserted-by":"crossref","unstructured":"An, W., Tian, F., Chen, P., Tang, S., Zheng, Q., & Wang, Q. (2022). Fine-grained category discovery under coarse-grained supervision with hierarchical weighted self-contrastive learning. arXiv preprint arXiv:2210.07733.","DOI":"10.18653\/v1\/2022.emnlp-main.85"},{"key":"2343_CR4","unstructured":"An, W., Tian, F., Shi, W., Chen, Y., Wu, Y., Wang, Q., & Chen, P. (2023b). Transfer & alignment network for generalized category discovery. arXiv preprint arXiv:2312.16467."},{"key":"2343_CR5","doi-asserted-by":"crossref","unstructured":"An, W., Tian, F., Zheng, Q., Ding, W., Wang, Q., & Chen, P. (2023c). Generalized category discovery with decoupled prototypical network. In AAAI Conference on artificial intelligence (AAAI), (pp. 12527\u201312535)","DOI":"10.1609\/aaai.v37i11.26475"},{"key":"2343_CR6","doi-asserted-by":"crossref","unstructured":"Assran, M., Caron, M., Misra, I., Bojanowski, P., Bordes, F., Vincent, P., Joulin, A., Rabbat, M., & Ballas, N. (2022). Masked siamese networks for label-efficient learning. In European conference on computer vision (ECCV), (pp. 456\u2013473)","DOI":"10.1007\/978-3-031-19821-2_26"},{"key":"2343_CR7","doi-asserted-by":"crossref","unstructured":"Assran, M., Caron, M., Misra, I., Bojanowski, P., Joulin, A., Ballas, N., & Rabbat, M. (2021). Semi-supervised learning of visual features by non-parametrically predicting view assignments with support samples. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 8443\u20138452)","DOI":"10.1109\/ICCV48922.2021.00833"},{"key":"2343_CR8","unstructured":"Bai, J., Liu, Z., Wang, H., Chen, R., Mu, L., Li, X., Zhou, J.\u00a0T., Feng, Y., Wu, J., & Hu, H. (2023). Towards distribution-agnostic generalized category discovery. arXiv preprint arXiv:2310.01376."},{"key":"2343_CR9","doi-asserted-by":"crossref","unstructured":"Banerjee, A., Kallooriyakath, L.\u00a0S., & Biswas, S. (2024). Amend: Adaptive margin and expanded neighborhood for efficient generalized category discovery. In IEEE\/CVF Winter conference on applications of computer vision (WACV), (pp. 2101\u20132110).","DOI":"10.1109\/WACV57701.2024.00210"},{"key":"2343_CR10","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.\u00a0D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et\u00a0al. (2020). Language models are few-shot learners. In Conference on neural information processing systems (NeurIPS), (pp. 1877\u20131901)"},{"key":"2343_CR11","unstructured":"Cao, K., Brbic, M., & Leskovec, J. (2022). Open-world semi-supervised learning. In International conference on learning representations (ICLR)"},{"key":"2343_CR12","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020). Unsupervised learning of visual features by contrasting cluster assignments. In Conference on neural information processing systems (NeurIPS), (pp. 9912\u20139924)"},{"key":"2343_CR13","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 9650\u20139660)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2343_CR14","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., & Soricut, R. (2021). Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 3558\u20133568)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"2343_CR15","doi-asserted-by":"crossref","unstructured":"Chen, G., Peng, P., Huang, Y., Geng, M., & Tian, Y. (2024). Adaptive discovering and merging for incremental novel class discovery. arXiv preprint arXiv:2403.03382.","DOI":"10.1609\/aaai.v38i10.29006"},{"key":"2343_CR16","doi-asserted-by":"crossref","unstructured":"Chen, X. & He, K. (2021). Exploring simple siamese representation learning. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 15750\u201315758)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"2343_CR17","doi-asserted-by":"crossref","unstructured":"Cherti, M., Beaumont, R., Wightman, R., Wortsman, M., Ilharco, G., Gordon, C., Schuhmann, C., Schmidt, L., & Jitsev, J. (2023). Reproducible scaling laws for contrastive language-image learning. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 2818\u20132829).","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"2343_CR18","unstructured":"Chi, H., Liu, F., Yang, W., Lan, L., Liu, T., Han, B., Niu, G., Zhou, M., & Sugiyama, M. (2022). Meta discovery: Learning to discover novel classes given very limited data. In International conference on learning representations (ICLR)"},{"key":"2343_CR19","doi-asserted-by":"crossref","unstructured":"Chiaroni, F., Dolz, J., Masud, Z.\u00a0I., Mitiche, A., & Ben\u00a0Ayed, I. (2023). Parametric information maximization for generalized category discovery. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 1729\u20131739).","DOI":"10.1109\/ICCV51070.2023.00166"},{"key":"2343_CR20","unstructured":"Chuyu, Z., Ruijie, X., & Xuming, H. (2023). Novel class discovery for long-tailed recognition. Transactions on Machine Learning Research."},{"key":"2343_CR21","unstructured":"Conti, A., Fini, E., Mancini, M., Rota, P., Wang, Y., & Ricci, E. (2023). Vocabulary-free image classification. In Conference on neural information processing systems (NeurIPS), (pp. 30662\u201330680)"},{"key":"2343_CR22","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 248\u2013255).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2343_CR23","unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In Conference of the North American chapter of the association for computational linguistics: human language technologies (NAACL-HLT), (pp. 4171\u20134186)"},{"key":"2343_CR24","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International conference on learning representations (ICLR)"},{"key":"2343_CR25","doi-asserted-by":"crossref","unstructured":"Du, R., Chang, D., Liang, K., Hospedales, T., Song, Y.-Z., & Ma, Z. (2023). On-the-fly category discovery. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (pp. 11691\u201311700)","DOI":"10.1109\/CVPR52729.2023.01125"},{"key":"2343_CR26","doi-asserted-by":"crossref","unstructured":"Fan, J., Liu, D., Chang, H., Huang, H., Chen, M., & Cai, W. (2024). Seeing unseen: Discover novel biomedical concepts via geometry-constrained probabilistic modeling. arXiv preprint arXiv:2403.01053.","DOI":"10.1109\/CVPR52733.2024.01095"},{"key":"2343_CR27","unstructured":"Fan, L., Krishnan, D., Isola, P., Katabi, D., & Tian, Y. (2023). Improving clip training with language rewrites. In Conference on neural information processing systems (NeurIPS), (pp. 35544\u201335575)"},{"key":"2343_CR28","unstructured":"Fei, Y., Zhao, Z., Yang, S., & Zhao, B. (2022). Xcon: Learning with experts for fine-grained category discovery. In The British machine vision conference (BMVC), (pp. 96)."},{"key":"2343_CR29","doi-asserted-by":"crossref","unstructured":"Feng, J., Yang, Y., Xie, Y., Li, Y., Guo, Y., Guo, Y., He, Y., Xiang, L., & Ding, G. (2024). Debiased novel category discovering and localization. arXiv preprint arXiv:2402.18821.","DOI":"10.1609\/aaai.v38i2.27943"},{"key":"2343_CR30","doi-asserted-by":"crossref","unstructured":"Feng, W., Ju, L., Wang, L., Song, K., & Ge, Z. (2023). Towards novel class discovery: A study in novel skin lesions clustering. In International conference on medical image computing and computer-assisted intervention, (pp. 24\u201333), Springer.","DOI":"10.1007\/978-3-031-43987-2_3"},{"key":"2343_CR31","doi-asserted-by":"crossref","unstructured":"Fini, E., Sangineto, E., Lathuili\u00e8re, S., Zhong, Z., Nabi, M., & Ricci, E. (2021). A unified objective for novel class discovery. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 9284\u20139292)","DOI":"10.1109\/ICCV48922.2021.00915"},{"key":"2343_CR32","doi-asserted-by":"crossref","unstructured":"Gao, F., Zhong, W., Cao, Z., Peng, X., & Li, Z. (2023a). Opengcd: Assisting open world recognition with generalized category discovery. arXiv preprint arXiv:2308.06926.","DOI":"10.2139\/ssrn.4903867"},{"key":"2343_CR33","doi-asserted-by":"crossref","unstructured":"Gao, P., Geng, S., Zhang, R., Ma, T., Fang, R., Zhang, Y., Li, H., & Qiao, Y. (2023b). CLIP-adapter: Better vision-language models with feature adapters. International Journal of Computer Vision, 1\u201315.","DOI":"10.1007\/s11263-023-01891-x"},{"key":"2343_CR34","unstructured":"Ge, C., Huang, R., Xie, M., Lai, Z., Song, S., Li, S., & Huang, G. (2023). Domain adaptation via prompt learning. IEEE Transactions on Neural Networks and Learning Systems."},{"key":"2343_CR35","unstructured":"Goel, S., Bansal, H., Bhatia, S., Rossi, R., Vinay, V., & Grover, A. (2022). Cyclip: Cyclic contrastive language-image pretraining. In Conference on neural information processing systems (NeurIPS), (pp. 6704\u20136719)"},{"issue":"6","key":"2343_CR36","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S. J., & Tao, D. (2021). Knowledge distillation: A survey. International Journal of Computer Vision, 129(6), 1789\u20131819.","journal-title":"International Journal of Computer Vision"},{"key":"2343_CR37","doi-asserted-by":"crossref","unstructured":"Gu, P., Zhang, C., Xu, R., & He, X. (2023). Class-relation knowledge distillation for novel class discovery. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 16474\u201316483)","DOI":"10.1109\/ICCV51070.2023.01510"},{"key":"2343_CR38","unstructured":"Guo, L.-Z., Zhang, Y.-G., Wu, Z.-F., Shao, J.-J., & Li, Y.-F. (2022). Robust semi-supervised learning when not all classes have labels. In Conference on neural information processing systems (NeurIPS), (pp. 3305\u20133317)"},{"key":"2343_CR39","unstructured":"Han, K., Li, Y., Vaze, S., Li, J., & Jia, X. (2023). What\u2019s in a name? beyond class indices for image recognition. arXiv preprint arXiv:2304.02364."},{"key":"2343_CR40","unstructured":"Han, K., Rebuffi, S.-A., Ehrhardt, S., Vedaldi, A., & Zisserman, A. (2020). Automatically discovering and learning new visual categories with ranking statistics. In International conference on learning representations (ICLR)"},{"issue":"10","key":"2343_CR41","doi-asserted-by":"publisher","first-page":"6767","DOI":"10.1109\/TPAMI.2021.3091944","volume":"44","author":"K Han","year":"2022","unstructured":"Han, K., Rebuffi, S.-A., Ehrhardt, S., Vedaldi, A., & Zisserman, A. (2022). Autonovel: Automatically discovering and learning novel visual categories. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10), 6767\u20136781.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2343_CR42","doi-asserted-by":"crossref","unstructured":"Han, K., Vedaldi, A., & Zisserman, A. (2019). Learning to discover novel visual categories via deep transfer clustering. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 8401\u20138409).","DOI":"10.1109\/ICCV.2019.00849"},{"key":"2343_CR43","unstructured":"Hao, S., Han, K., & Wong, K.-Y.\u00a0K. (2023). Cipr: An efficient framework with cross-instance positive relations for generalized category discovery. arXiv preprint arXiv:2304.06928."},{"key":"2343_CR44","doi-asserted-by":"crossref","unstructured":"Hasan, Z., Ahmed, M., Faridee, A. Z.\u00a0M., Purushotham, S., Kwon, H., Lee, H., & Roy, N. (2023a). Nev-ncd: Negative learning, entropy, and variance regularization based novel action categories discovery. In IEEE International conference on image processing (ICIP), (pp. 2720\u20132724)","DOI":"10.1109\/ICIP49359.2023.10222474"},{"key":"2343_CR45","unstructured":"Hasan, Z., Faridee, A. Z.\u00a0M., Ahmed, M., Purushotham, S., Kwon, H., Lee, H., & Roy, N. (2023b). Novel categories discovery from probability matrix perspective. arXiv preprint arXiv:2307.03856."},{"key":"2343_CR46","unstructured":"Hayes, T.\u00a0L., de\u00a0Souza, C.\u00a0R., Kim, N., Kim, J., Volpi, R., & Larlus, D. (2024). Pandas: Prototype-based novel class discovery and detection. arXiv preprint arXiv:2402.17420."},{"key":"2343_CR47","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In IEEE\/CVF conference on computer vision and pattern recognition (CVPR), (pp. 770\u2013778)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2343_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107383","volume":"110","author":"Y He","year":"2021","unstructured":"He, Y., Shen, Z., & Cui, P. (2021). Towards non-iid image classification: A dataset and baselines. Pattern Recognition, 110, 107383.","journal-title":"Pattern Recognition"},{"key":"2343_CR49","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531."},{"key":"2343_CR50","doi-asserted-by":"crossref","unstructured":"Hogan, W., Li, J., & Shang, J. (2023). Open-world semi-supervised generalized relation discovery aligned in a real-world setting. arXiv preprint arXiv:2305.13533.","DOI":"10.18653\/v1\/2023.emnlp-main.880"},{"key":"2343_CR51","unstructured":"Hsu, Y.-C., Lv, Z., & Kira, Z. (2018). Learning to cluster in order to transfer across domains and tasks. In International conference on learning representations (ICLR)"},{"key":"2343_CR52","unstructured":"Hsu, Y.-C., Lv, Z., Schlosser, J., Odom, P., & Kira, Z. (2019). Multi-class classification without multi-class labels. In International conference on learning representations (ICLR)"},{"key":"2343_CR53","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.-T., Parekh, Z., Pham, H., Le, Q., Sung, Y.-H., Li, Z., & Duerig, T. (2021a). Scaling up visual and vision-language representation learning with noisy text supervision. In International conference on machine learning (ICML), (pp. 4904\u20134916)"},{"key":"2343_CR54","doi-asserted-by":"crossref","unstructured":"Jia, X., Han, K., Zhu, Y., & Green, B. (2021b). Joint representation learning and novel category discovery on single-and multi-modal data. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 610\u2013619)","DOI":"10.1109\/ICCV48922.2021.00065"},{"key":"2343_CR55","doi-asserted-by":"crossref","unstructured":"Joseph, K., Paul, S., Aggarwal, G., Biswas, S., Rai, P., Han, K., & Balasubramanian, V.\u00a0N. (2022a). Novel class discovery without forgetting. In European conference on computer vision (ECCV), (pp. 570\u2013586)","DOI":"10.1007\/978-3-031-20053-3_33"},{"key":"2343_CR56","doi-asserted-by":"crossref","unstructured":"Joseph, K., Paul, S., Aggarwal, G., Biswas, S., Rai, P., Han, K., & Balasubramanian, V.\u00a0N. (2022b). Spacing loss for discovering novel categories. In IEEE\/CVF Conference on computer vision and pattern recognition workshops (CVPRW), (pp. 3761\u20133766)","DOI":"10.1109\/CVPRW56347.2022.00420"},{"key":"2343_CR57","doi-asserted-by":"crossref","unstructured":"Khattak, M.\u00a0U., Rasheed, H., Maaz, M., Khan, S., & Khan, F.\u00a0S. (2023). Maple: Multi-modal prompt learning. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 19113\u201319122)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"2343_CR58","doi-asserted-by":"crossref","unstructured":"Kim, H., Suh, S., Kim, D., Jeong, D., Cho, H., & Kim, J. (2023). Proxy anchor-based unsupervised learning for continuous generalized category discovery. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 16688\u201316697)","DOI":"10.1109\/ICCV51070.2023.01530"},{"key":"2343_CR59","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., & Fei-Fei, L. (2013). 3d object representations for fine-grained categorization. In IEEE\/CVF International conference on computer vision workshops (ICCVW), (pp. 554\u2013561)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"2343_CR60","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.-J., Shamma, D. A., et al. (2017). Visual genome: Connecting language and vision using crowdsourced dense image annotations. International Journal of Computer Vision, 123, 32\u201373.","journal-title":"International Journal of Computer Vision"},{"key":"2343_CR61","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al. (2009). Learning multiple layers of features from tiny images. Master\u2019s thesis, Department of Computer Science, University of Toronto."},{"issue":"1\u20132","key":"2343_CR62","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H. W. (1955). The hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2(1\u20132), 83\u201397.","journal-title":"Naval Research Logistics Quarterly"},{"key":"2343_CR63","unstructured":"Kumar, A., Raghunathan, A., Jones, R., Ma, T., & Liang, P. (2022). Fine-tuning can distort pretrained features and underperform out-of-distribution. In International conference on learning representations (ICLR)"},{"issue":"7","key":"2343_CR64","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., et al. (2020). The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. International Journal of Computer Vision, 128(7), 1956\u20131981.","journal-title":"International Journal of Computer Vision"},{"key":"2343_CR65","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., & Constant, N. (2021). The power of scale for parameter-efficient prompt tuning. In Conference on empirical methods in natural language processing (EMNLP)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"2343_CR66","unstructured":"Li, J., Savarese, S., & Hoi, S. (2023a). Masked unsupervised self-training for label-free image classification. In International conference on learning representations (ICLR)"},{"key":"2343_CR67","doi-asserted-by":"crossref","unstructured":"Li, J., Xiong, C., & Hoi, S.\u00a0C. (2021). Comatch: Semi-supervised learning with contrastive graph regularization. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 9475\u20139484)","DOI":"10.1109\/ICCV48922.2021.00934"},{"key":"2343_CR68","unstructured":"Li, Q., Ma, Q., Nie, W., & Liu, A. (2023b). Reinforcement learning based multi-modal feature fusion network for novel class discovery. arXiv preprint arXiv:2308.13801."},{"key":"2343_CR69","doi-asserted-by":"crossref","unstructured":"Li, W., Fan, Z., Huo, J., & Gao, Y. (2023c). Modeling inter-class and intra-class constraints in novel class discovery. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 3449\u20133458)","DOI":"10.1109\/CVPR52729.2023.00336"},{"key":"2343_CR70","doi-asserted-by":"crossref","unstructured":"Li, X.\u00a0L. & Liang, P. (2021). Prefix-tuning: Optimizing continuous prompts for generation. In Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"2343_CR71","unstructured":"Li, Z., Dai, B., Simsek, F., Meinel, C., & Yang, H. (2023d). Imbagcd: Imbalanced generalized category discovery. In IEEE\/CVF Conference on computer vision and pattern recognition workshops (CVPRW)."},{"key":"2343_CR72","unstructured":"Li, Z., Meinel, C., & Yang, H. (2023e). Generalized categories discovery for long-tailed recognition. arXiv preprint arXiv:2401.05352."},{"key":"2343_CR73","unstructured":"Li, Z., Otholt, J., Dai, B., Hu, D., Meinel, C., & Yang, H. (2023f). Supervised knowledge may hurt novel class discovery performance. Transactions on Machine Learning Research."},{"key":"2343_CR74","unstructured":"Li, Z., Otholt, J., Dai, B., Meinel, C., Yang, H., et\u00a0al. (2022). A closer look at novel class discovery from the labeled set. arXiv preprint arXiv:2209.09120."},{"key":"2343_CR75","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.\u00a0L. (2014). Microsoft coco: Common objects in context. In European conference on computer vision (ECCV), (pp. 740\u2013755)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2343_CR76","doi-asserted-by":"crossref","unstructured":"Liu, J., Wang, Y., Zhang, T., Fan, Y., Yang, Q., & Shao, J. (2023a). Open-world semi-supervised novel class discovery. In International joint conference on artificial intelligence (IJCAI), (pp. 4002\u20134010)","DOI":"10.24963\/ijcai.2023\/445"},{"key":"2343_CR77","unstructured":"Liu, M., Roy, S., Li, W., Zhong, Z., Sebe, N., & Ricci, E. (2024). Democratizing fine-grained visual recognition with large language models. In International conference on learning representations (ICLR)"},{"key":"2343_CR78","doi-asserted-by":"crossref","unstructured":"Liu, M., Roy, S., Zhong, Z., Sebe, N., & Ricci, E. (2023b). Large-scale pre-trained models are surprisingly strong in incremental novel class discovery. arXiv preprint arXiv:2303.15975.","DOI":"10.1007\/978-3-031-78444-6_9"},{"issue":"9","key":"2343_CR79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Computing Surveys, 55(9), 1\u201335.","journal-title":"ACM Computing Surveys"},{"key":"2343_CR80","doi-asserted-by":"crossref","unstructured":"Liu, Y. & Tuytelaars, T. (2022). Residual tuning: Toward novel category discovery without labels. IEEE Transactions on Neural Networks and Learning Systems.","DOI":"10.1109\/TNNLS.2022.3140235"},{"key":"2343_CR81","doi-asserted-by":"crossref","unstructured":"Ma, S., Zhu, F., Zhong, Z., Zhang, X.-Y., & Liu, C.-L. (2024). Active generalized category discovery. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 16890\u201316900)","DOI":"10.1109\/CVPR52733.2024.01598"},{"key":"2343_CR82","unstructured":"MacQueen, J. (1965). Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth berkeley symposium on mathematical statistics and probability, (pp. 281)"},{"key":"2343_CR83","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., & Vedaldi, A. (2013). Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151."},{"key":"2343_CR84","unstructured":"Marczak, D., Rype\u015b\u0107, G., Cygert, S., Trzci\u0144ski, T., & Twardowski, B. (2023). Generalized continual category discovery. arXiv preprint arXiv:2308.12112."},{"key":"2343_CR85","unstructured":"Mayilvahanan, P., Wiedemer, T., Rusak, E., Bethge, M., & Brendel, W. (2024). Does CLIP\u2019s generalization performance mainly stem from high train-test similarity? In International conference on learning representations (ICLR)"},{"key":"2343_CR86","doi-asserted-by":"crossref","unstructured":"Menon, S., Chandratreya, I.\u00a0P., & Vondrick, C. (2023). Task bias in contrastive vision-language models. International Journal of Computer Vision, 1\u201315.","DOI":"10.1007\/s11263-023-01945-0"},{"key":"2343_CR87","unstructured":"Nayak, N.\u00a0V., Yu, P., & Bach, S.\u00a0H. (2023). Learning to compose soft prompts for compositional zero-shot learning. In International conference on learning representations (ICLR)"},{"key":"2343_CR88","doi-asserted-by":"crossref","unstructured":"Otholt, J., Meinel, C., & Yang, H. (2024). Guided cluster aggregation: A hierarchical approach to generalized category discovery. In IEEE\/CVF Winter conference on applications of computer vision (WACV), (pp. 2618\u20132627)","DOI":"10.1109\/WACV57701.2024.00260"},{"key":"2343_CR89","unstructured":"Ouldnoughi, R., Kuo, C.-W., & Kira, Z. (2023). CLIP-GCD: Simple language guided generalized category discovery. arXiv preprint arXiv:2305.10420."},{"key":"2343_CR90","doi-asserted-by":"crossref","unstructured":"Parkhi, O.\u00a0M., Vedaldi, A., Zisserman, A., & Jawahar, C. (2012). Cats and dogs. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 3498\u20133505)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"2343_CR91","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et\u00a0al. (2019). Pytorch: An imperative style, high-performance deep learning library. In Conference on neural information processing systems (NeurIPS)"},{"key":"2343_CR92","unstructured":"Peng, Z., Tian, Q., Xu, J., Jin, Y., Lu, X., Tan, X., Xie, Y., & Ma, L. (2023). Generalized category discovery in semantic segmentation. arXiv preprint arXiv:2311.11525."},{"key":"2343_CR93","doi-asserted-by":"crossref","unstructured":"Pu, N., Li, W., Ji, X., Qin, Y., Sebe, N., & Zhong, Z. (2024). Federated generalized category discovery. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 28741\u201328750)","DOI":"10.1109\/CVPR52733.2024.02715"},{"key":"2343_CR94","doi-asserted-by":"crossref","unstructured":"Pu, N., Zhong, Z., & Sebe, N. (2023). Dynamic conceptional contrastive learning for generalized category discovery. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 3479\u20133488)","DOI":"10.1109\/CVPR52729.2023.00339"},{"key":"2343_CR95","doi-asserted-by":"crossref","unstructured":"Qin, G. & Eisner, J. (2021). Learning how to ask: Querying lms with mixtures of soft prompts. In Proceedings of the 2021 conference of the North American chapter of the association for computational linguistics: human language technologies","DOI":"10.18653\/v1\/2021.naacl-main.410"},{"key":"2343_CR96","unstructured":"Radford, A., Kim, J.\u00a0W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al. (2021). Learning transferable visual models from natural language supervision. In International conference on machine learning (ICML), (pp. 8748\u20138763)"},{"key":"2343_CR97","unstructured":"Rastegar, S., Doughty, H., & Snoek, C.\u00a0G. (2023). Learn to categorize or categorize to learn? self-coding for generalized category discovery. In Conference on neural information processing systems (NeurIPS)"},{"key":"2343_CR98","doi-asserted-by":"crossref","unstructured":"Ren, S., Li, L., Ren, X., Zhao, G., & Sun, X. (2023a). Delving into the openness of CLIP. In Findings of the Association for Computational Linguistics (ACL), 9587\u20139606.","DOI":"10.18653\/v1\/2023.findings-acl.610"},{"key":"2343_CR99","unstructured":"Ren, S., Zhang, A., Zhu, Y., Zhang, S., Zheng, S., Li, M., Smola, A.\u00a0J., & Sun, X. (2023b). Prompt pre-training with twenty-thousand classes for open-vocabulary visual recognition. In Conference on neural information processing systems (NeurIPS), (pp. 12569\u201312588)"},{"key":"2343_CR100","doi-asserted-by":"crossref","unstructured":"Riz, L., Saltori, C., Ricci, E., & Poiesi, F. (2023). Novel class discovery for 3d point cloud semantic segmentation. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 9393\u20139402)","DOI":"10.1109\/CVPR52729.2023.00906"},{"key":"2343_CR101","doi-asserted-by":"crossref","unstructured":"Rizve, M.\u00a0N., Kardan, N., Khan, S., Khan, F.\u00a0S., & Shah, M. (2022a). Openldn: Learning to discover novel classes for open-world semi-supervised learning. In European conference on computer vision (ECCV), (pp. 382\u2013401)","DOI":"10.1007\/978-3-031-19821-2_22"},{"key":"2343_CR102","doi-asserted-by":"crossref","unstructured":"Rizve, M.\u00a0N., Kardan, N., & Shah, M. (2022b). Towards realistic semi-supervised learning. In European conference on computer vision (ECCV), (pp. 437\u2013455)","DOI":"10.1007\/978-3-031-19821-2_25"},{"key":"2343_CR103","doi-asserted-by":"crossref","unstructured":"Roy, S., Liu, M., Zhong, Z., Sebe, N., & Ricci, E. (2022). Class-incremental novel class discovery. In European conference on computer vision (ECCV), (pp. 317\u2013333)","DOI":"10.1007\/978-3-031-19827-4_19"},{"issue":"3","key":"2343_CR104","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"2343_CR105","unstructured":"Schuhmann, C., Vencu, R., Beaumont, R., Kaczmarczyk, R., Mullis, C., Katta, A., Coombes, T., Jitsev, J., & Komatsuzaki, A. (2021). Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114."},{"key":"2343_CR106","doi-asserted-by":"crossref","unstructured":"Shin, T., Razeghi, Y., Logan\u00a0IV, R.\u00a0L., Wallace, E., & Singh, S. (2020). Autoprompt: Eliciting knowledge from language models with automatically generated prompts. In Conference on empirical methods in natural language processing (EMNLP), (pp. 4222\u20134235)","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"2343_CR107","unstructured":"Sohn, K., Berthelot, D., Carlini, N., Zhang, Z., Zhang, H., Raffel, C.\u00a0A., Cubuk, E.\u00a0D., Kurakin, A., & Li, C.-L. (2020). Fixmatch: Simplifying semi-supervised learning with consistency and confidence. In Conference on neural information processing systems (NeurIPS), (pp. 596\u2013608)"},{"key":"2343_CR108","doi-asserted-by":"crossref","unstructured":"Stevens, S., Wu, J., Thompson, M.\u00a0J., Campolongo, E.\u00a0G., Song, C.\u00a0H., Carlyn, D.\u00a0E., Dong, L., Dahdul, W.\u00a0M., Stewart, C., Berger-Wolf, T., et\u00a0al. (2024). BioCLIP: A vision foundation model for the tree of life. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 19412\u201319424)","DOI":"10.1109\/CVPR52733.2024.01836"},{"key":"2343_CR109","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., & Cao, Y. (2023a). Eva-clip: Improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389."},{"key":"2343_CR110","unstructured":"Sun, Y. & Li, Y. (2023). Opencon: Open-world contrastive learning. Transactions on Machine Learning Research."},{"key":"2343_CR111","unstructured":"Sun, Y., Shi, Z., & Li, Y. (2024). A graph-theoretic framework for understanding open-world semi-supervised learning. In Conference on neural information processing systems (NeurIPS)"},{"key":"2343_CR112","unstructured":"Sun, Y., Shi, Z., Liang, Y., & Li, Y. (2023b). When and how does known class help discover unknown ones? provable understanding through spectral analysis. In International conference on machine learning (ICML), (pp. 33014\u201333043)"},{"key":"2343_CR113","unstructured":"Tan, K.\u00a0C., Liu, Y., Ambrose, B., Tulig, M., & Belongie, S. (2019). The herbarium challenge 2019 dataset. arXiv preprint arXiv:1906.05372."},{"key":"2343_CR114","doi-asserted-by":"crossref","unstructured":"Troisemaine, C., Flocon-Cholet, J., Gosselin, S., Vaton, S., Reiffers-Masson, A., & Lemaire, V. (2022). A method for discovering novel classes in tabular data. In IEEE International conference on knowledge graph (ICKG), (pp. 265\u2013274)","DOI":"10.1109\/ICKG55886.2022.00041"},{"key":"2343_CR115","unstructured":"Troisemaine, C., Lemaire, V., Gosselin, S., Reiffers-Masson, A., Flocon-Cholet, J., & Vaton, S. (2023a). Novel class discovery: an introduction and key concepts. arXiv preprint arXiv:2302.12028."},{"key":"2343_CR116","doi-asserted-by":"crossref","unstructured":"Troisemaine, C., Reiffers-Masson, A., Gosselin, S., Lemaire, V., & Vaton, S. (2023b). A practical approach to novel class discovery in tabular data. arXiv preprint arXiv:2311.05440.","DOI":"10.1007\/978-3-031-43430-3_18"},{"issue":"1","key":"2343_CR117","first-page":"3221","volume":"15","author":"L Van Der Maaten","year":"2014","unstructured":"Van Der Maaten, L. (2014). Accelerating t-sne using tree-based algorithms. Journal of Machine Learning Research, 15(1), 3221\u20133245.","journal-title":"Journal of Machine Learning Research"},{"key":"2343_CR118","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.\u00a0N., Kaiser, \u0141., and Polosukhin, I. (2017). Attention is all you need. In Conference on neural information processing systems (NeurIPS), (pp. 5998\u20136008)"},{"key":"2343_CR119","doi-asserted-by":"crossref","unstructured":"Vaze, S., Han, K., Vedaldi, A., & Zisserman, A. (2022a). Generalized category discovery. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 7492\u20137501)","DOI":"10.1109\/CVPR52688.2022.00734"},{"key":"2343_CR120","unstructured":"Vaze, S., Han, K., Vedaldi, A., & Zisserman, A. (2022b). Open-set recognition: A good closed-set classifier is all you need. In International conference on learning representations (ICLR)"},{"key":"2343_CR121","doi-asserted-by":"crossref","unstructured":"Vaze, S., Vedaldi, A., & Zisserman, A. (2023). No representation rules them all in category discovery. In Conference on neural information processing systems (NeurIPS)","DOI":"10.1109\/CVPR52688.2022.00734"},{"key":"2343_CR122","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., & Belongie, S. (2011). The caltech-ucsd birds-200-2011 dataset. California Institute of Technology."},{"key":"2343_CR123","unstructured":"Wang, E., Peng, Z., Xie, Z., Liu, X., & Cheng, M.-M. (2024a). Get: Unlocking the multi-modal potential of clip for generalized category discovery. arXiv preprint arXiv:2403.09974."},{"key":"2343_CR124","unstructured":"Wang, H., Vaze, S., & Han, K. (2024b). Sptnet: An efficient alternative framework for generalized category discovery with spatial prompt tuning. In International conference on learning representations (ICLR)."},{"key":"2343_CR125","doi-asserted-by":"crossref","unstructured":"Wang, H., Yang, M., Wei, K., & Deng, C. (2023a). Hierarchical prompt learning for compositional zero-shot recognition. In International Joint conference on artificial intelligence (IJCAI), (pp.1470\u20131478).","DOI":"10.24963\/ijcai.2023\/163"},{"key":"2343_CR126","unstructured":"Wang, J., Zhang, L., Liu, J., Guo, T., & Wu, W. (2024c). Learning from semi-factuals: A debiased and semantic-aware framework for generalized relation discovery. arXiv preprint arXiv:2401.06327."},{"key":"2343_CR127","unstructured":"Wang, L., Liu, C., Guo, J., Dong, J., Wang, X., Huang, H., & Zhu, Q. (2023b). Federated continual novel class learning. arXiv preprint arXiv:2312.13500."},{"key":"2343_CR128","doi-asserted-by":"crossref","unstructured":"Wang, W., Lei, T., Chen, Q., & Liu, Y. (2024d). Semantic-guided novel category discovery. In AAAI Conference on artificial intelligence (AAAI)","DOI":"10.1609\/aaai.v38i6.28371"},{"key":"2343_CR129","unstructured":"Wang, W., Sun, Q., Zhang, F., Tang, Y., Liu, J., & Wang, X. (2024e). Diffusion feedback helps clip see better. arXiv preprint arXiv:2407.20171."},{"issue":"1","key":"2343_CR130","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1007\/s11263-023-01868-w","volume":"132","author":"Y Wang","year":"2024","unstructured":"Wang, Y., Yu, Z., Wang, J., Heng, Q., Chen, H., Ye, W., Xie, R., Xie, X., & Zhang, S. (2024). Exploring vision-language models for imbalanced learning. International Journal of Computer Vision, 132(1), 224\u2013237.","journal-title":"International Journal of Computer Vision"},{"key":"2343_CR131","unstructured":"Wang, Y., Zhong, Z., Qiao, P., Cheng, X., Zheng, X., Liu, C., Sebe, N., Ji, R., & Chen, J. (2024g). Discover and align taxonomic context priors for open-world semi-supervised learning. In Conference on neural information processing systems (NeurIPS)."},{"key":"2343_CR132","doi-asserted-by":"crossref","unstructured":"Wang, Z., Salehi, B., Gritsenko, A., Chowdhury, K., Ioannidis, S., & Dy, J. (2020). Open-world class discovery with kernel networks. In IEEE International conference on data mining (ICDM), (pp. 631\u2013640)","DOI":"10.1109\/ICDM50108.2020.00072"},{"key":"2343_CR133","doi-asserted-by":"crossref","unstructured":"Wen, X., Zhao, B., & Qi, X. (2023). Parametric classification for generalized category discovery: A baseline study. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 16590\u201316600)","DOI":"10.1109\/ICCV51070.2023.01521"},{"key":"2343_CR134","unstructured":"Weng, T., Xiao, J., & Jiang, H. (2024). Decompose novel into known: Part concept learning for 3d novel class discovery. In Conference on neural information processing systems (NeurIPS)."},{"key":"2343_CR135","doi-asserted-by":"crossref","unstructured":"Wortsman, M., Ilharco, G., Kim, J.\u00a0W., Li, M., Kornblith, S., Roelofs, R., Lopes, R.\u00a0G., Hajishirzi, H., Farhadi, A., Namkoong, H., et\u00a0al. (2022). Robust fine-tuning of zero-shot models. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 7959\u20137971)","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"2343_CR136","unstructured":"Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., & Duan, N. (2023a). Visual chatgpt: Talking, drawing and editing with visual foundation models. arXiv preprint arXiv:2303.04671."},{"key":"2343_CR137","unstructured":"Wu, L., Li, J., Wang, Y., Meng, Q., Qin, T., Chen, W., Zhang, M., Liu, T.-Y., et\u00a0al. (2021). R-drop: Regularized dropout for neural networks. In Conference on neural information processing systems (NeurIPS), (pp. 10890\u201310905)"},{"key":"2343_CR138","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chi, Z., Wang, Y., & Feng, S. (2023b). Metagcd: Learning to continually learn in generalized category discovery. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 1655\u20131665)","DOI":"10.1109\/ICCV51070.2023.00159"},{"key":"2343_CR139","unstructured":"Xu, H., Xie, S., Tan, X.\u00a0E., Huang, P.-Y., Howes, R., Sharma, V., Li, S.-W., Ghosh, G., Zettlemoyer, L., & Feichtenhofer, C. (2024). Demystifying clip data. In International conference on learning representations (ICLR)"},{"key":"2343_CR140","doi-asserted-by":"crossref","unstructured":"Yang, M., Wang, L., Deng, C., & Zhang, H. (2023a). Bootstrap your own prior: Towards distribution-agnostic novel class discovery. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 3459\u20133468)","DOI":"10.1109\/CVPR52729.2023.00337"},{"key":"2343_CR141","doi-asserted-by":"crossref","unstructured":"Yang, M., Zhu, Y., Yu, J., Wu, A., & Deng, C. (2022). Divide and conquer: Compositional experts for generalized novel class discovery. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 14268\u201314277)","DOI":"10.1109\/CVPR52688.2022.01387"},{"key":"2343_CR142","doi-asserted-by":"crossref","unstructured":"Yang, X., Pan, X., King, I., & Xu, Z. (2023b). Generalized category discovery with clustering assignment consistency. arXiv preprint arXiv:2310.19210.","DOI":"10.1007\/978-981-99-8073-4_41"},{"key":"2343_CR143","doi-asserted-by":"crossref","unstructured":"Ye, B., Gan, K., Wei, T., & Zhang, M.-L. (2023). Bridging the gap: Learning pace synchronization for open-world semi-supervised learning. arXiv preprint arXiv:2309.11930.","DOI":"10.24963\/ijcai.2024\/593"},{"key":"2343_CR144","doi-asserted-by":"crossref","unstructured":"Yu, Q., Ikami, D., Irie, G., & Aizawa, K. (2022). Self-labeling framework for novel category discovery over domains. In AAAI Conference on artificial intelligence (AAAI), (pp. 3161\u20133169)","DOI":"10.1609\/aaai.v36i3.20224"},{"key":"2343_CR145","unstructured":"Yuan, L., Chen, D., Chen, Y.-L., Codella, N., Dai, X., Gao, J., Hu, H., Huang, X., Li, B., Li, C., et\u00a0al. (2021). Florence: A new foundation model for computer vision. arXiv preprint arXiv:2111.11432."},{"key":"2343_CR146","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., & Loy, C.\u00a0C. (2022). Unified vision and language prompt learning. arXiv preprint arXiv:2210.07225."},{"key":"2343_CR147","doi-asserted-by":"crossref","unstructured":"Zang, Z., Shang, L., Yang, S., Wang, F., Sun, B., Xie, X., & Li, S.\u00a0Z. (2023). Boosting novel category discovery over domains with soft contrastive learning and all in one classifier. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 11858\u201311867)","DOI":"10.1109\/ICCV51070.2023.01089"},{"key":"2343_CR148","unstructured":"Zhang, C., Hu, C., Xu, R., Gao, Z., He, Q., & He, X. (2022a). Mutual information-guided knowledge transfer for novel class discovery. arXiv preprint arXiv:2206.12063."},{"key":"2343_CR149","unstructured":"Zhang, J., Ma, X., Guo, S., & Xu, W. (2023a). Towards unbiased training in federated open-world semi-supervised learning. In International conference on machine learning (ICML), (pp. 41498\u201341509)"},{"key":"2343_CR150","unstructured":"Zhang, L., Qi, L., Yang, X., Qiao, H., Yang, M.-H., & Liu, Z. (2022b). Automatically discovering novel visual categories with self-supervised prototype learning. arXiv preprint arXiv:2208.00979."},{"key":"2343_CR151","doi-asserted-by":"crossref","unstructured":"Zhang, R., Zhang, W., Fang, R., Gao, P., Li, K., Dai, J., Qiao, Y., & Li, H. (2022c). Tip-adapter: Training-free adaption of CLIP for few-shot classification. In European conference on computer vision (ECCV), (pp. 493\u2013510)","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"2343_CR152","doi-asserted-by":"crossref","unstructured":"Zhang, S., Khan, S., Shen, Z., Naseer, M., Chen, G., & Khan, F. (2023b). Promptcal: Contrastive affinity learning via auxiliary prompts for generalized novel category discovery. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 2765\u20132775)","DOI":"10.1109\/CVPR52729.2023.00339"},{"key":"2343_CR153","doi-asserted-by":"crossref","unstructured":"Zhang, S., Naseer, M., Chen, G., Shen, Z., Khan, S., Zhang, K., & Khan, F.\u00a0S. (2024a). S3a: Towards realistic zero-shot classification via self structural semantic alignment. In AAAI Conference on artificial intelligence (AAAI), (pp. 7278\u20137286)","DOI":"10.1609\/aaai.v38i7.28557"},{"key":"2343_CR154","unstructured":"Zhang, X., Jiang, J., Feng, Y., Wu, Z.-F., Zhao, X., Wan, H., Tang, M., Jin, R., & Gao, Y. (2022d). Grow and merge: A unified framework for continuous categories discovery. In Conference on neural information processing systems (NeurIPS), (pp. 27455\u201327468)"},{"key":"2343_CR155","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Huang, X., Ma, J., Li, Z., Luo, Z., Xie, Y., Qin, Y., Luo, T., Li, Y., Liu, S., et\u00a0al. (2024b). Recognize anything: A strong image tagging model. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 1724\u20131732)","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"2343_CR156","unstructured":"Zhao, B. & Han, K. (2021). Novel visual category discovery with dual ranking statistics and mutual knowledge distillation. In Conference on neural information processing systems (NeurIPS), (pp. 22982\u201322994)"},{"key":"2343_CR157","doi-asserted-by":"crossref","unstructured":"Zhao, B. & Mac\u00a0Aodha, O. (2023). Incremental generalized category discovery. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 19137\u201319147)","DOI":"10.1109\/ICCV51070.2023.01753"},{"key":"2343_CR158","doi-asserted-by":"crossref","unstructured":"Zhao, B., Wen, X., & Han, K. (2023). Learning semi-supervised gaussian mixture models for generalized category discovery. In IEEE\/CVF International conference on computer vision (ICCV), (pp. 16623\u201316633)","DOI":"10.1109\/ICCV51070.2023.01524"},{"key":"2343_CR159","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zhong, Z., Sebe, N., & Lee, G.\u00a0H. (2022). Novel class discovery in semantic segmentation. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 4340\u20134349)","DOI":"10.1109\/CVPR52688.2022.00430"},{"key":"2343_CR160","doi-asserted-by":"crossref","unstructured":"Zheng, J., Li, W., Hong, J., Petersson, L., & Barnes, N. (2022). Towards open-set object detection and discovery. In IEEE\/CVF Conference on computer vision and pattern recognition workshops (CVPRW), (pp. 3961\u20133970)","DOI":"10.1109\/CVPRW56347.2022.00441"},{"key":"2343_CR161","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Fini, E., Roy, S., Luo, Z., Ricci, E., & Sebe, N. (2021a). Neighborhood contrastive learning for novel class discovery. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 10867\u201310875)","DOI":"10.1109\/CVPR46437.2021.01072"},{"key":"2343_CR162","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zhu, L., Luo, Z., Li, S., Yang, Y., & Sebe, N. (2021b). Openmix: Reviving known knowledge for discovering novel visual categories in an open world. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 9462\u20139470)","DOI":"10.1109\/CVPR46437.2021.00934"},{"key":"2343_CR163","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.\u00a0C., & Liu, Z. (2022a). Conditional prompt learning for vision-language models. In IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), (pp. 16816\u201316825)","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"2343_CR164","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C. C., & Liu, Z. (2022). Learning to prompt for vision-language models. International Journal of Computer Vision, 130(9), 2337\u20132348.","DOI":"10.1007\/s11263-022-01653-1"},{"key":"2343_CR165","unstructured":"Zhu, F., Ma, S., Cheng, Z., Zhang, X.-Y., Zhang, Z., & Liu, C.-L. (2024). Open-world machine learning: A review and new outlooks. arXiv preprint arXiv:2403.01759."},{"key":"2343_CR166","unstructured":"Zhuang, J., Chen, Z., Wei, P., Li, G., & Lin, L. (2022). Open set domain adaptation by novel class discovery. In IEEE International conference on multimedia and expo (ICME)"}],"updated-by":[{"DOI":"10.1007\/s11263-025-02449-9","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000}}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02343-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02343-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02343-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T02:02:17Z","timestamp":1749261737000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02343-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,20]]},"references-count":166,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["2343"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02343-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,20]]},"assertion":[{"value":"21 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 April 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The article has been corrected.","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2025","order":7,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":8,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":9,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s11263-025-02449-9","URL":"https:\/\/doi.org\/10.1007\/s11263-025-02449-9","order":10,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}