{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:35:39Z","timestamp":1791912939696,"version":"4.3.4"},"reference-count":97,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T00:00:00Z","timestamp":1728345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Singapore MOE AcRF Tier 2","award":["MOE-T2EP20120-0001"],"award-info":[{"award-number":["MOE-T2EP20120-0001"]}]},{"name":"Singapore MOE AcRF Tier 2","award":["MOE-T2EP20221-0012"],"award-info":[{"award-number":["MOE-T2EP20221-0012"]}]},{"name":"RIE2020 Industry Alignment Fund Industry Collaboration Projects (IAF-ICP) Funding Initiative","award":["I1901E0052"],"award-info":[{"award-number":["I1901E0052"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s11263-024-02223-3","type":"journal-article","created":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T02:04:04Z","timestamp":1728353044000},"page":"1456-1475","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation"],"prefix":"10.1007","volume":"133","author":[{"given":"Jiahao","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangtai","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yew Soon","family":"Ong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5345-1591","authenticated-orcid":false,"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,8]]},"reference":[{"key":"2223_CR1","unstructured":"Baranchuk, D., Rubachev, I., Voynov, A., Khrulkov, V., Babenko, A. (2022) Label-efficient semantic segmentation with diffusion models. In ICLR"},{"key":"2223_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Poole, B. (2016) The fast bilateral solver. In ECCV","DOI":"10.1007\/978-3-319-46487-9_38"},{"key":"2223_CR3","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M. (2020) Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934"},{"issue":"4","key":"2223_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592116","volume":"42","author":"H Chefer","year":"2023","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., & Cohen-Or, D. (2023). Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models. ACM Transactions on Graphics (TOG), 42(4), 1\u201310.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"2223_CR5","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., Zhang, Z., Cheng, D., Zhu, C., Cheng, T., Zhao, Q., Li, B., Lu, X., Zhu, R., Wu, Y., Dai, J., Wang, J., Shi, J., Ouyang, W., Loy, C.C., Lin, D. (2019) MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155"},{"key":"2223_CR6","unstructured":"Chen, P., Sheng, K., Zhang, M., Shen, Y., Li, K., Shen, C. (2022) Open vocabulary object detection with proposal mining and prediction equalization. arXiv preprint arXiv:2206.11134"},{"key":"2223_CR7","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B. (2016) The cityscapes dataset for semantic urban scene understanding. In CVPR","DOI":"10.1109\/CVPR.2016.350"},{"key":"2223_CR8","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 CVPR","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2223_CR9","unstructured":"Di\u00a0Stefano, L., Bulgarelli, A. (1999) A simple and efficient connected components labeling algorithm. In ICIAP"},{"key":"2223_CR10","doi-asserted-by":"crossref","unstructured":"Du, Y., Wei, F., Zhang, Z., Shi, M., Gao, Y., Li, G. (2022) Learning to prompt for open-vocabulary object detection with vision-language model. In CVPR","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"2223_CR11","doi-asserted-by":"crossref","unstructured":"Dvornik, N., Mairal, J., Schmid, C. (2018) Modeling visual context is key to augmenting object detection datasets. In ECCV","DOI":"10.1007\/978-3-030-01258-8_23"},{"key":"2223_CR12","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Misra, I., Hebert, M. (2017) Cut, paste and learn: Surprisingly easy synthesis for instance detection. In ICCV","DOI":"10.1109\/ICCV.2017.146"},{"key":"2223_CR13","doi-asserted-by":"crossref","unstructured":"Fang, H. S., Sun, J., Wang, R., Gou, M., Li, Y. L., Lu, C. (2019) Instaboost: Boosting instance segmentation via probability map guided copy-pasting. In ICCV","DOI":"10.1109\/ICCV.2019.00077"},{"key":"2223_CR14","doi-asserted-by":"crossref","unstructured":"Gal, R., Arar, M., Atzmon, Y., Bermano, A.H., Chechik, G., Cohen-Or, D. (2023) Designing an encoder for fast personalization of text-to-image models. arXiv preprint arXiv:2302.12228","DOI":"10.1145\/3610548.3618173"},{"key":"2223_CR15","doi-asserted-by":"crossref","unstructured":"Gao, M., Xing, C., Niebles, J. C., Li, J., Xu, R., Liu, W., Xiong, C. (2022) Open vocabulary object detection with pseudo bounding-box labels. In ECCV","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"2223_CR16","unstructured":"Ge, Y., Xu, J., Zhao, B. N., Itti, L., Vineet, V. (2022) Dall-e for detection: Language-driven context image synthesis for object detection. arXiv preprint arXiv:2206.09592"},{"key":"2223_CR17","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Cui, Y., Srinivas, A., Qian, R., Lin, T.Y., Cubuk, E.D., Le, Q.V., Zoph, B. (2021) Simple copy-paste is a strong data augmentation method for instance segmentation. In CVPR","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"2223_CR18","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Gu, X., Cui, Y., Lin, T.Y. (2022) Scaling open-vocabulary image segmentation with image-level labels. In ECCV","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"2223_CR19","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y. (2022) Open-vocabulary object detection via vision and language knowledge distillation. In ICLR"},{"key":"2223_CR20","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R. (2019) Lvis: A dataset for large vocabulary instance segmentation. In CVPR","DOI":"10.1109\/CVPR.2019.00550"},{"key":"2223_CR21","unstructured":"Han, J., Niu, M., Du, Z., Wei, L., Xie, L., Zhang, X., Tian, Q. (2020) Joint coco and lvis workshop at eccv 2020: Lvis challenge track technical report: Asynchronous semi-supervised learning for large vocabulary instance segmentation. In ECCVW"},{"key":"2223_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J. (2016) Deep residual learning for image recognition. In CVPR","DOI":"10.1109\/CVPR.2016.90"},{"key":"2223_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R. (2017) Mask r-cnn. In ICCV","DOI":"10.1109\/ICCV.2017.322"},{"key":"2223_CR24","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D. (2023) Prompt-to-prompt image editing with cross attention control. In ICLR"},{"key":"2223_CR25","doi-asserted-by":"crossref","unstructured":"Hinterstoisser, S., Lepetit, V., Wohlhart, P., Konolige, K .(2018) On pre-trained image features and synthetic images for deep learning. In ECCV Workshops","DOI":"10.1007\/978-3-030-11009-3_42"},{"key":"2223_CR26","doi-asserted-by":"crossref","unstructured":"Hu, X., Jiang, Y., Tang, K., Chen, J., Miao, C., Zhang, H. (2020) Learning to segment the tail. In CVPR","DOI":"10.1109\/CVPR42600.2020.01406"},{"key":"2223_CR27","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.T., Parekh, Z., Pham, H., Le, Q., Sung, Y.H., Li, Z., Duerig, T. (2021) Scaling up visual and vision-language representation learning with noisy text supervision. In ICML"},{"key":"2223_CR28","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S. (2022) Elucidating the design space of diffusion-based generative models. arXiv preprint arXiv:2206.00364"},{"key":"2223_CR29","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T. (2014) Referitgame: Referring to objects in photographs of natural scenes. In EMNLP","DOI":"10.3115\/v1\/D14-1086"},{"key":"2223_CR30","unstructured":"Kingma, D.P., Welling, M. (2014) Auto-encoding variational bayes. In ICLR"},{"key":"2223_CR31","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et\u00a0al (2023) Segment anything. In ICCV","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2223_CR32","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y. (2022) Multi-concept customization of text-to-image diffusion. arXiv preprint arXiv:2212.04488","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"2223_CR33","unstructured":"Kuo, W., Cui, Y., Gu, X., Piergiovanni, A., Angelova, A. (2023) F-vlm: Open-vocabulary object detection upon frozen vision and language models. In ICLR"},{"issue":"7","key":"2223_CR34","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":"2223_CR35","doi-asserted-by":"crossref","unstructured":"Lai, X., Tian, Z., Chen, Y., Li, Y., Yuan, Y., Liu, S., Jia, J. (2024) Lisa: Reasoning segmentation via large language model. In CVPR","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"2223_CR36","unstructured":"Li, B,. Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R. (2022a) Language-driven semantic segmentation. In ICLR"},{"key":"2223_CR37","doi-asserted-by":"crossref","unstructured":"Li, D., Ling, H., Kim, SW., Kreis, K., Fidler, S., Torralba, A. (2022b) Bigdatasetgan: Synthesizing imagenet with pixel-wise annotations. In CVPR","DOI":"10.1109\/CVPR52688.2022.02064"},{"key":"2223_CR38","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, T., Kang, B., Tang, S., Wang, C., Li, J., Feng, J. (2020) Overcoming classifier imbalance for long-tail object detection with balanced group softmax. In CVPR","DOI":"10.1109\/CVPR42600.2020.01100"},{"key":"2223_CR39","unstructured":"Li, Z., Zhou, Q., Zhang, X., Zhang, Y., Wang, Y., Xie, W. (2023) Guiding text-to-image diffusion model towards grounded generation. arXiv preprint arXiv:2301.05221"},{"key":"2223_CR40","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L. (2014) Microsoft coco: Common objects in context. In ECCV","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2223_CR41","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S. (2017) Feature pyramid networks for object detection. In CVPR","DOI":"10.1109\/CVPR.2017.106"},{"key":"2223_CR42","doi-asserted-by":"crossref","unstructured":"Liu, J., Sun, Y., Han, C., Dou, Z., Li, W. (2020) Deep representation learning on long-tailed data: A learnable embedding augmentation perspective. In CVPR","DOI":"10.1109\/CVPR42600.2020.00304"},{"key":"2223_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B. (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2223_CR44","unstructured":"Loshchilov, I., Hutter, F. (2017) Sgdr: Stochastic gradient descent with warm restarts. In ICLR"},{"key":"2223_CR45","unstructured":"Loshchilov, I., Hutter, F. (2019) Decoupled weight decay regularization. In ICLR"},{"key":"2223_CR46","unstructured":"Lu, H., Liu, W., Zhang, B., Wang, B., Dong, K., Liu, B., Sun, J., Ren, T., Li, Z., Sun, Y., et\u00a0al (2024) Deepseek-vl: towards real-world vision-language understanding. arXiv preprint arXiv:2403.05525"},{"key":"2223_CR47","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A, Camburu, O., Yuille, A.L., Murphy, K. (2016) Generation and comprehension of unambiguous object descriptions. In CVPR","DOI":"10.1109\/CVPR.2016.9"},{"issue":"11","key":"2223_CR48","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G. A. (1995). Wordnet: A lexical database for english. Communications of the ACM, 38(11), 39\u201341.","journal-title":"Communications of the ACM"},{"key":"2223_CR49","doi-asserted-by":"crossref","unstructured":"Minderer, M., Gritsenko, A., Stone, A., Neumann, M., Weissenborn, D., Dosovitskiy, A., Mahendran, A., Arnab, A., Dehghani, M., Shen, Z., et\u00a0al (2022) Simple open-vocabulary object detection with vision transformers. In ECCV","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"2223_CR50","unstructured":"OpenAI (2023) Gpt-4 technical report. arXiv preprint arXiv:2303.08774"},{"key":"2223_CR51","first-page":"62","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Trans SMC, 9, 62.","journal-title":"IEEE Trans SMC"},{"key":"2223_CR52","doi-asserted-by":"crossref","unstructured":"Parmar, G., Singh, K.K., Zhang, R., Li, Y., Lu, J., Zhu, J.Y. (2023) Zero-shot image-to-image translation. arXiv preprint arXiv:2302.03027","DOI":"10.1145\/3588432.3591513"},{"key":"2223_CR53","doi-asserted-by":"crossref","unstructured":"Phung, Q., Ge, S., Huang, J. B. (2023) Grounded text-to-image synthesis with attention refocusing. arXiv preprint arXiv:2306.05427","DOI":"10.1109\/CVPR52733.2024.00758"},{"key":"2223_CR54","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., Rombach, R. (2023) Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952"},{"key":"2223_CR55","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al (2021a) Learning transferable visual models from natural language supervision. In ICML"},{"key":"2223_CR56","unstructured":"Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J. (2021b) Learning transferable visual models from natural language supervision. In ICML"},{"key":"2223_CR57","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M. (2022) Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125"},{"key":"2223_CR58","unstructured":"Rasheed, H., Maaz, M., Khattak, M.U., Khan, S., Khan, F.S. (2022) Bridging the gap between object and image-level representations for open-vocabulary detection. In NeurIPS"},{"key":"2223_CR59","doi-asserted-by":"crossref","unstructured":"Rasheed, H., Maaz, M., Shaji, S., Shaker, A., Khan, S., Cholakkal, H., Anwer, R.M., Xing, E., Yang, M.H., Khan, F.S. (2024) Glamm: Pixel grounding large multimodal model. In CVPR","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"2223_CR60","unstructured":"Ren, J., Yu, C., Ma, X., Zhao, H., Yi, S., et\u00a0al (2020) Balanced meta-softmax for long-tailed visual recognition. In NeurIPS"},{"key":"2223_CR61","doi-asserted-by":"crossref","unstructured":"Richter, S. R., Vineet, V., Roth, S., Koltun, V. (2016) Playing for data: Ground truth from computer games. In ECCV","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"2223_CR62","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B. (2022) High-resolution image synthesis with latent diffusion models. In CVPR","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2223_CR63","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T. (2015) U-net: Convolutional networks for biomedical image segmentation. In MICCAI","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2223_CR64","doi-asserted-by":"crossref","unstructured":"Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E., Ghasemipour, S.K.S., Ayan, B.K., Mahdavi, S.S., Lopes, R.G., et\u00a0al (2022) Photorealistic text-to-image diffusion models with deep language understanding. In NeurIPS","DOI":"10.1145\/3528233.3530757"},{"key":"2223_CR65","doi-asserted-by":"crossref","unstructured":"Shao, S., Li, Z., Zhang, T., Peng, C., Yu, G., Zhang, X., Li, J., Sun, J. (2019) Objects365: A large-scale, high-quality dataset for object detection. In ICCV","DOI":"10.1109\/ICCV.2019.00852"},{"key":"2223_CR66","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R. (2018) Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning. In ACL","DOI":"10.18653\/v1\/P18-1238"},{"key":"2223_CR67","doi-asserted-by":"crossref","unstructured":"Su, H., Qi, C.R., Li, Y., Guibas, L.J. (2015) Render for cnn: Viewpoint estimation in images using cnns trained with rendered 3d model views. In ICCV","DOI":"10.1109\/ICCV.2015.308"},{"key":"2223_CR68","doi-asserted-by":"crossref","unstructured":"Tan, J., Wang, C., Li, B., Li, Q., Ouyang, W., Yin, C., Yan, J. (2020a) Equalization loss for long-tailed object recognition. In CVPR","DOI":"10.1109\/CVPR42600.2020.01168"},{"key":"2223_CR69","unstructured":"Tan, J., Zhang, G., Deng, H., Wang, C., Lu, L., Li, Q., Dai, J. (2020b) 1st place solution of lvis challenge 2020: A good box is not a guarantee of a good mask. arXiv preprint arXiv:2009.01559"},{"key":"2223_CR70","doi-asserted-by":"crossref","unstructured":"Tan, J., Lu, X., Zhang, G., Yin, C., Li, Q. (2021) Equalization loss v2: A new gradient balance approach for long-tailed object detection. In CVPR","DOI":"10.1109\/CVPR46437.2021.00173"},{"key":"2223_CR71","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V. (2020c) Efficientdet: Scalable and efficient object detection. In CVPR","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"2223_CR72","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M. A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F. (2023a) Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971"},{"key":"2223_CR73","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et\u00a0al (2023b) Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288"},{"key":"2223_CR74","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, W., Zang, Y., Cao, Y., Pang, J., Gong, T., Chen, K., Liu, Z., Loy, C.C., Lin, D. (2021a) Seesaw loss for long-tailed instance segmentation. In CVPR","DOI":"10.1109\/CVPR46437.2021.00957"},{"key":"2223_CR75","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, P., Chu, T., Cao, Y., Zhou, Y., Wu, T., Wang, B., He, C., Lin, D. (2023) V3det: Vast vocabulary visual detection dataset. In ICCV","DOI":"10.1109\/ICCV51070.2023.01817"},{"key":"2223_CR76","doi-asserted-by":"crossref","unstructured":"Wang, T., Li, Y., Kang, B., Li, J., Liew, J., Tang, S., Hoi, S., Feng, J. (2020) The devil is in classification: A simple framework for long-tail instance segmentation. In ECCV","DOI":"10.1007\/978-3-030-58568-6_43"},{"key":"2223_CR77","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, Y., Zhao, C., Zeng, W., Wang, J., Tang, M. (2021b) Adaptive class suppression loss for long-tail object detection. In CVPR","DOI":"10.1109\/CVPR46437.2021.00312"},{"key":"2223_CR78","unstructured":"Waqas, Z. S., Arora, A., Gupta, A., Khan, S., Sun, G., Khan, S. F., Zhu, F., Shao, L., Xia, G. S., Bai, X. (2019) isaid: A large-scale dataset for instance segmentation in aerial images. In CVPRW"},{"key":"2223_CR79","unstructured":"Wei, F., Gao, Y., Wu, Z., Hu, H., Lin, S. (2021) Aligning pretraining for detection via object-level contrastive learning. In NeurIPS"},{"key":"2223_CR80","doi-asserted-by":"crossref","unstructured":"Wu, J., Song, L., Wang, T., Zhang, Q., Yuan, J. (2020) Forest r-cnn: Large-vocabulary long-tailed object detection and instance segmentation. In ACM-MM","DOI":"10.1145\/3394171.3413970"},{"key":"2223_CR81","unstructured":"Wu, J., Li, X., Xu, S., Yuan, H., Ding, H., Yang, Y., Li, X., Zhang, J., Tong, Y., Jiang, X., Ghanem, B., Tao, D. (2023) Towards open vocabulary learning: A survey. arXiv preprint arXiv:2306.15880"},{"key":"2223_CR82","unstructured":"Wu, S., Jin, S., Zhang, W., Xu, L., Liu, W., Li, W., Loy, C. C. (2024) F-lmm: Grounding frozen large multimodal models. arXiv preprint arXiv:2406.05821"},{"key":"2223_CR83","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R. (2019) Detectron2"},{"key":"2223_CR84","doi-asserted-by":"crossref","unstructured":"Xie, J., Li, Y., Huang, Y., Liu, H., Zhang, W., Zheng, Y., Shou, M.Z. (2023) Boxdiff: Text-to-image synthesis with training-free box-constrained diffusion. In ICCV","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"2223_CR85","doi-asserted-by":"crossref","unstructured":"Zang, Y., Huang, C., Loy, C.C. (2021) Fasa: Feature augmentation and sampling adaptation for long-tailed instance segmentation. In ICCV","DOI":"10.1109\/ICCV48922.2021.00344"},{"key":"2223_CR86","doi-asserted-by":"crossref","unstructured":"Zang, Y., Li, W., Zhou, K., Huang, C., Loy, C.C. (2022) Open-vocabulary detr with conditional matching. In ECCV","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"2223_CR87","doi-asserted-by":"crossref","unstructured":"Zareian, A., Rosa, K.D., Hu, D.H., Chang, S.F. (2021) Open-vocabulary object detection using captions. In CVPR","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"2223_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, C., Pan, T. Y., Li, Y., Hu, H., Xuan, D., Changpinyo, S., Gong, B., Chao, W. L. (2021a) Mosaicos: A simple and effective use of object-centric images for long-tailed object detection. In ICCV","DOI":"10.1109\/ICCV48922.2021.00047"},{"key":"2223_CR89","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S. (2023) Vision-language models for vision tasks: A survey. arXiv preprint arXiv:2304.00685"},{"key":"2223_CR90","doi-asserted-by":"crossref","unstructured":"Zhang, S., Li, Z., Yan, S., He, X., Sun, J. (2021b) Distribution alignment: A unified framework for long-tail visual recognition. In CVPR","DOI":"10.1109\/CVPR46437.2021.00239"},{"key":"2223_CR91","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Ling, H., Gao, J., Yin, K., Lafleche, J. F., Barriuso, A., Torralba, A., Fidler, S. (2021c) Datasetgan: Efficient labeled data factory with minimal human effort. In CVPR","DOI":"10.1109\/CVPR46437.2021.01001"},{"key":"2223_CR92","unstructured":"Zhao, H., Sheng, D., Bao, J., Chen, D., Chen, D., Wen, F., Yuan, L., Liu, C., Zhou, W., Chu, Q., Zhang, W., Yu, N. (2023) X-paste: Revisiting scalable copy-paste for instance segmentation using clip and stablediffusion. In ICML"},{"key":"2223_CR93","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Yang, J., Zhang, P., Li, C., Codella, N., Li, L.H., Zhou, L., Dai, X., Yuan, L., Li, Y., et\u00a0al (2022) Regionclip: Region-based language-image pretraining. In CVPR","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"2223_CR94","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z. (2022a) Conditional prompt learning for vision-language models. In CVPR","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"2223_CR95","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P. (2021) Probabilistic two-stage detection. arXiv preprint arXiv:2103.07461"},{"key":"2223_CR96","doi-asserted-by":"crossref","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I. (2022b) Detecting twenty-thousand classes using image-level supervision. In ECCV","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"2223_CR97","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y. (2023) Detrs with collaborative hybrid assignments training. In ICCV","DOI":"10.1109\/ICCV51070.2023.00621"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02223-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02223-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02223-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T18:12:53Z","timestamp":1743358373000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02223-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,8]]},"references-count":97,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["2223"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02223-3","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,8]]},"assertion":[{"value":"25 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}