{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:55:58Z","timestamp":1768406158654,"version":"3.49.0"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730092","type":"print"},{"value":"9783031730108","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"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\/978-3-031-73010-8_3","type":"book-chapter","created":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T13:12:22Z","timestamp":1731157942000},"page":"35-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Learning the\u00a0Unlearned: Mitigating Feature Suppression in\u00a0Contrastive Learning"],"prefix":"10.1007","author":[{"given":"Jihai","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Xiang","family":"Lan","sequence":"additional","affiliation":[]},{"given":"Xiaoye","family":"Qu","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Mengling","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Bryan","family":"Hooi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,10]]},"reference":[{"key":"3_CR1","unstructured":"Assran, M., et al.: The hidden uniform cluster prior in self-supervised learning. arXiv preprint arXiv:2210.07277 (2022)"},{"issue":"8","key":"3_CR2","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798\u20131828 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR3","unstructured":"Bleeker, M., Yates, A., de\u00a0Rijke, M.: Reducing predictive feature suppression in resource-constrained contrastive image-caption retrieval. Trans. Mach. Learn. Res. (2023)"},{"key":"3_CR4","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural. Inf. Process. Syst. 33, 9912\u20139924 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"3_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"3_CR7","first-page":"11834","volume":"34","author":"T Chen","year":"2021","unstructured":"Chen, T., Luo, C., Li, L.: Intriguing properties of contrastive losses. Adv. Neural. Inf. Process. Syst. 34, 11834\u201311845 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR8","unstructured":"Chen, T.S., Hung, W.C., Tseng, H.Y., Chien, S.Y., Yang, M.H.: Incremental false negative detection for contrastive learning. arXiv preprint arXiv:2106.03719 (2021)"},{"key":"3_CR9","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning (2020)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"3_CR12","unstructured":"Chu, T., et al.: Image clustering via the principle of rate reduction in the age of pretrained models. arXiv preprint arXiv:2306.05272 (2023)"},{"key":"3_CR13","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 215\u2013223. JMLR Workshop and Conference Proceedings (2011)"},{"key":"3_CR14","unstructured":"Federici, M., Dutta, A., Forr\u00e9, P., Kushman, N., Akata, Z.: Learning robust representations via multi-view information bottleneck. arXiv preprint arXiv:2002.07017 (2020)"},{"key":"3_CR15","unstructured":"Gandelsman, Y., Efros, A.A., Steinhardt, J.: Interpreting CLIP\u2019s image representation via text-based decomposition. arXiv preprint arXiv:2310.05916 (2023)"},{"key":"3_CR16","first-page":"27356","volume":"34","author":"S Ge","year":"2021","unstructured":"Ge, S., Mishra, S., Li, C.L., Wang, H., Jacobs, D.: Robust contrastive learning using negative samples with diminished semantics. Adv. Neural. Inf. Process. Syst. 34, 27356\u201327368 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR17","unstructured":"Grill, J.B., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)"},{"key":"3_CR18","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 297\u2013304. JMLR Workshop and Conference Proceedings (2010)"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR21","first-page":"9995","volume":"33","author":"K Hermann","year":"2020","unstructured":"Hermann, K., Lampinen, A.: What shapes feature representations? exploring datasets, architectures, and training. Adv. Neural. Inf. Process. Syst. 33, 9995\u201310006 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR22","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"issue":"1","key":"3_CR23","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3390\/technologies9010002","volume":"9","author":"A Jaiswal","year":"2020","unstructured":"Jaiswal, A., Babu, A.R., Zadeh, M.Z., Banerjee, D., Makedon, F.: A survey on contrastive self-supervised learning. Technologies 9(1), 2 (2020)","journal-title":"Technologies"},{"key":"3_CR24","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images. Technical report, Toronto, ON, Canada (2009)"},{"key":"3_CR25","unstructured":"Kukleva, A., B\u00f6hle, M., Schiele, B., Kuehne, H., Rupprecht, C.: Temperature schedules for self-supervised contrastive methods on long-tail data. arXiv preprint arXiv:2303.13664 (2023)"},{"key":"3_CR26","doi-asserted-by":"publisher","unstructured":"Lan, X., Ng, D., Hong, S., Feng, M.: Intra-inter subject self-supervised learning for multivariate cardiac signals. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 4, pp. 4532\u20134540 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i4.20376, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/20376","DOI":"10.1609\/aaai.v36i4.20376"},{"key":"3_CR27","unstructured":"Lan, X., Yan, H., Hong, S., Feng, M.: Towards enhancing time series contrastive learning: a dynamic bad pair mining approach. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=K2c04ulKXn"},{"key":"3_CR28","unstructured":"LeCun, Y., Cortes, C., Burges, C.: MNIST handwritten digit database. ATT Labs 2 (2010). http:\/\/yann.lecun.com\/exdb\/mnist"},{"key":"3_CR29","doi-asserted-by":"crossref","unstructured":"Leng, S., et al.: Mitigating object hallucinations in large vision-language models through visual contrastive decoding. arXiv preprint arXiv:2311.16922 (2023)","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., Wang, J., Zhao, W.X., Wen, J.R.: Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"3_CR31","unstructured":"Liu, F., Lin, K., Li, L., Wang, J., Yacoob, Y., Wang, L.: Mitigating hallucination in large multi-modal models via robust instruction tuning. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"3_CR32","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"issue":"1","key":"3_CR33","first-page":"857","volume":"35","author":"X Liu","year":"2021","unstructured":"Liu, X., et al.: Self-supervised learning: generative or contrastive. IEEE Trans. Knowl. Data Eng. 35(1), 857\u2013876 (2021)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"3_CR34","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Large-scale CelebFaces attributes (CelebA) dataset. Retrieved August 15(2018), 11 (2018)"},{"key":"3_CR35","unstructured":"Mishra, S., et al.: Learning visual representations for transfer learning by suppressing texture. arXiv preprint arXiv:2011.01901 (2020)"},{"key":"3_CR36","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"3_CR37","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"3_CR38","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125, vol. 1, no. 2, p. 3 (2022)"},{"key":"3_CR39","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"3_CR40","first-page":"4974","volume":"34","author":"J Robinson","year":"2021","unstructured":"Robinson, J., Sun, L., Yu, K., Batmanghelich, K., Jegelka, S., Sra, S.: Can contrastive learning avoid shortcut solutions? Adv. Neural. Inf. Process. Syst. 34, 4974\u20134986 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR41","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"3_CR42","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Shah, A., Sra, S., Chellappa, R., Cherian, A.: Max-margin contrastive learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 8220\u20138230 (2022)","DOI":"10.1609\/aaai.v36i8.20796"},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Shvetsova, N., Chen, B., Rouditchenko, A., Thomas, S., Kingsbury, B., Feris, R.S., Harwath, D., Glass, J., Kuehne, H.: Everything at once-multi-modal fusion transformer for video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20020\u201320029 (2022)","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"3_CR45","unstructured":"Tamkin, A., Glasgow, M., He, X., Goodman, N.: Feature dropout: revisiting the role of augmentations in contrastive learning. arXiv preprint arXiv:2212.08378 (2022)"},{"key":"3_CR46","doi-asserted-by":"crossref","unstructured":"Tong, S., Liu, Z., Zhai, Y., Ma, Y., LeCun, Y., Xie, S.: Eyes wide shut? Exploring the visual shortcomings of multimodal LLMs. arXiv preprint arXiv:2401.06209 (2024)","DOI":"10.1109\/CVPR52733.2024.00914"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Van\u00a0Gansbeke, W., Vandenhende, S., Georgoulis, S., Van\u00a0Gool, L.: Unsupervised semantic segmentation by contrasting object mask proposals. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10052\u201310062 (2021)","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"3_CR48","unstructured":"Woo, G., Liu, C., Sahoo, D., Kumar, A., Hoi, S.: CoST: contrastive learning of disentangled seasonal-trend representations for time series forecasting. arXiv preprint arXiv:2202.01575 (2022)"},{"key":"3_CR49","unstructured":"Xiao, T., Wang, X., Efros, A.A., Darrell, T.: What should not be contrastive in contrastive learning. arXiv preprint arXiv:2008.05659 (2020)"},{"key":"3_CR50","unstructured":"Xue, Y., Joshi, S., Gan, E., Chen, P.Y., Mirzasoleiman, B.: Which features are learnt by contrastive learning? On the role of simplicity bias in class collapse and feature suppression. arXiv preprint arXiv:2305.16536 (2023)"},{"key":"3_CR51","unstructured":"Yin, S., et al.: A survey on multimodal large language models. arXiv preprint arXiv:2306.13549 (2023)"},{"key":"3_CR52","doi-asserted-by":"crossref","unstructured":"Yue, Z., et al.: TS2Vec: towards universal representation of time series. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 8980\u20138987 (2022)","DOI":"10.1609\/aaai.v36i8.20881"},{"key":"3_CR53","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: LiT: zero-shot transfer with locked-image text tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"3_CR54","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"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\/978-3-031-73010-8_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T14:02:32Z","timestamp":1731160952000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73010-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,10]]},"ISBN":["9783031730092","9783031730108"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73010-8_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,10]]},"assertion":[{"value":"10 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"}}]}}