{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:49:43Z","timestamp":1777567783332,"version":"3.51.4"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733826","type":"print"},{"value":"9783031733833","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73383-3_25","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T12:07:20Z","timestamp":1730549240000},"page":"428-444","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Multi-label Cluster Discrimination for\u00a0Visual Representation Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4652-8296","authenticated-orcid":false,"given":"Xiang","family":"An","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6073-9014","authenticated-orcid":false,"given":"Kaicheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3236-8380","authenticated-orcid":false,"given":"Xiangzi","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8689-8366","authenticated-orcid":false,"given":"Ziyong","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3709-6216","authenticated-orcid":false,"given":"Jiankang","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"25_CR1","unstructured":"Qwen2 technical report (2024). https:\/\/qwenlm.github.io\/blog\/qwen2\/"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Abdelfattah, R., Guo, Q., Li, X., Wang, X., Wang, S.: CDUL: clip-driven unsupervised learning for multi-label image classification. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00130"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"An, X., et al.: Killing two birds with one stone: efficient and robust training of face recognition CNNs by partial fc. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00401"},{"key":"25_CR4","unstructured":"An, X., et al.: Unicom: universal and compact representation learning for image retrieval. In: ICLR (2023)"},{"key":"25_CR5","unstructured":"Asano, Y.M., Rupprecht, C., Vedaldi, A.: Self-labelling via simultaneous clustering and representation learning. In: ICLR (2020)"},{"key":"25_CR6","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv:2309.16609 (2023)"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"25_CR8","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: NeurIPS (2020)"},{"key":"25_CR9","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.E.: Big self-supervised models are strong semi-supervised learners. In: NeurIPS (2020)"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"25_CR12","unstructured":"Dao, T.: FlashAttention-2: faster attention with better parallelism and work partitioning. In: ICLR (2024)"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"25_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Gu, T., et al.: RWKV-CLIP: a robust vision-language representation learner. arXiv:2406.06973 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.276"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"25_CR19","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"25_CR20","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. IEEE Trans. Big Data (2019)"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A diagram is worth a dozen images. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"25_CR22","unstructured":"Li, J., Zhou, P., Xiong, C., Hoi, S.: Prototypical contrastive learning of unsupervised representations. In: ICLR (2020)"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: PatchCT: aligning patch set and label set with conditional transport for multi-label image classification. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01408"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, H., Hu, R., Feichtenhofer, C., He, K.: Scaling language-image pre-training via masking. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Li, Y., Song, Y., Luo, J.: Improving pairwise ranking for multi-label image classification. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.199"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"25_CR27","unstructured":"Liu, W., Tsang, I.W., M\u00fcller, K.R.: An easy-to-hard learning paradigm for multiple classes and multiple labels. JMLR (2017)"},{"key":"25_CR28","unstructured":"Liu, W., Wang, H., Shen, X., Tsang, I.W.: The emerging trends of multi-label learning. TPAMI (2021)"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Mahajan, D., et al.: Exploring the limits of weakly supervised pretraining. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"25_CR30","unstructured":"Micikevicius, P., et\u00a0al.: Mixed precision training. arXiv:1710.03740 (2017)"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Pham, K., et al.: Learning to predict visual attributes in the wild. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Qian, Q., Xu, Y., Hu, J., Li, H., Jin, R.: Unsupervised visual representation learning by online constrained k-means. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01614"},{"key":"25_CR34","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Ridnik, T., et al.: Asymmetric loss for multi-label classification. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00015"},{"key":"25_CR36","unstructured":"Schuhmann, C., et al.: Laion-400M: open dataset of clip-filtered 400 million image-text pairs. arXiv:2111.02114 (2021)"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Singh, M., et al.: Revisiting weakly supervised pre-training of visual perception models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00088"},{"key":"25_CR39","unstructured":"Su, J., Zhu, M., Murtadha, A., Pan, S., Wen, B., Liu, Y.: ZLPR: a novel loss for multi-label classification. arXiv:2208.02955 (2022)"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Sun, Y., et al.: Circle Loss: a unified perspective of pair similarity optimization. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"25_CR41","doi-asserted-by":"crossref","unstructured":"Tsoumakas, G., Katakis, I.: Multi-label classification: an overview. Int. J. Data Warehousing Min. (2007)","DOI":"10.4018\/978-1-59904-951-9.ch006"},{"key":"25_CR42","doi-asserted-by":"crossref","unstructured":"Wang, X., Han, X., Huang, W., Dong, D., Scott, M.R.: Multi-similarity loss with general pair weighting for deep metric learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00516"},{"key":"25_CR43","doi-asserted-by":"crossref","unstructured":"Xia, X., et al.: Holistic label correction for noisy multi-label classification. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00143"},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Yang, H., Tianyi\u00a0Zhou, J., Zhang, Y., Gao, B.B., Wu, J., Cai, J.: Exploit bounding box annotations for multi-label object recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.37"},{"key":"25_CR45","doi-asserted-by":"crossref","unstructured":"Yang, K., et al.: ALIP: adaptive language-image pre-training with synthetic caption. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00273"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"25_CR47","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: LiT: zero-shot transfer with locked-image text tuning. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"25_CR48","doi-asserted-by":"crossref","unstructured":"Zhan, X., Xie, J., Liu, Z., Ong, Y.S., Loy, C.C.: Online deep clustering for unsupervised representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00672"},{"key":"25_CR49","unstructured":"Zhang, M.L., Zhou, Z.H.: A review on multi-label learning algorithms. TKDE (2013)"},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, J., Yan, K., Zhao, Y., Guo, X., Huang, F., Li, J.: Transformer-based dual relation graph for multi-label image recognition. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00023"},{"key":"25_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, K., Fu, M., Wu, J.: Multi-label self-supervised learning with scene images. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00616"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73383-3_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T18:06:34Z","timestamp":1732989994000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73383-3_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031733826","9783031733833"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73383-3_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}