{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:56:28Z","timestamp":1776887788357,"version":"3.51.2"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729126","type":"print"},{"value":"9783031729133","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-72913-3_24","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T21:47:03Z","timestamp":1733089623000},"page":"430-447","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Contrastive Learning with\u00a0Synthetic Positives"],"prefix":"10.1007","author":[{"given":"Dewen","family":"Zeng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yawen","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinrong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyu","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Aberdam, A., et al.: Sequence-to-sequence contrastive learning for text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15302\u201315312 (2021)","DOI":"10.1109\/CVPR46437.2021.01505"},{"key":"24_CR2","unstructured":"Azizi, S., Kornblith, S., Saharia, C., Norouzi, M., Fleet, D.J.: Synthetic data from diffusion models improves ImageNet classification. arXiv preprint arXiv:2304.08466 (2023)"},{"key":"24_CR3","unstructured":"Balestriero, R., et\u00a0al.: A cookbook of self-supervised learning. arXiv preprint arXiv:2304.12210 (2023)"},{"key":"24_CR4","unstructured":"Baranchuk, D., Voynov, A., Rubachev, I., Khrulkov, V., Babenko, A.: Label-efficient semantic segmentation with diffusion models. In: International Conference on Learning Representations (2021)"},{"key":"24_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29"},{"key":"24_CR6","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: Advances in Neural Information Processing Systems, vol. 33, pp. 9912\u20139924 (2020)"},{"key":"24_CR7","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":"24_CR8","unstructured":"Chen, T., Kornblith, S., Swersky, K., Norouzi, M., Hinton, G.E.: Big self-supervised models are strong semi-supervised learners. In: Advances in Neural Information Processing Systems, vol. 33, pp. 22243\u201322255 (2020)"},{"key":"24_CR9","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"24_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":"24_CR11","unstructured":"Chuang, C.Y., Robinson, J., Lin, Y.C., Torralba, A., Jegelka, S.: Debiased contrastive learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 8765\u20138775 (2020)"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3606\u20133613 (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"24_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":"24_CR14","unstructured":"da\u00a0Costa, V.G.T., Fini, E., Nabi, M., Sebe, N., Ricci, E.: Solo-learn: a library of self-supervised methods for visual representation learning. J. Mach. Learn. Res. 23(56), 1\u20136 (2022). http:\/\/jmlr.org\/papers\/v23\/21-1155.html"},{"key":"24_CR15","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"24_CR16","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems, vol. 34, pp. 8780\u20138794 (2021)"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Dwibedi, D., Aytar, Y., Tompson, J., Sermanet, P., Zisserman, A.: With a little help from my friends: nearest-neighbor contrastive learning of visual representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9588\u20139597 (2021)","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Estepa, I.G., Sarasua, I., Nagarajan, B., Radeva, P.: ALL4One: symbiotic neighbour contrastive learning via self-attention and redundancy reduction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 16243\u201316253, October 2023","DOI":"10.1109\/ICCV51070.2023.01488"},{"key":"24_CR19","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: 2004 Conference on Computer Vision and Pattern Recognition Workshop, p. 178. IEEE (2004)"},{"key":"24_CR20","unstructured":"Grill, J.B., et al.: Bootstrap Your own latent-a new approach to self-supervised learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21271\u201321284 (2020)"},{"key":"24_CR21","unstructured":"Hassani, K., Khasahmadi, A.H.: Contrastive multi-view representation learning on graphs. In: International Conference on Machine Learning, pp. 4116\u20134126. PMLR (2020)"},{"key":"24_CR22","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":"24_CR23","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"24_CR24","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2021)"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Huynh, T., Kornblith, S., Walter, M.R., Maire, M., Khademi, M.: Boosting contrastive self-supervised learning with false negative cancellation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2785\u20132795 (2022)","DOI":"10.1109\/WACV51458.2022.00106"},{"key":"24_CR26","unstructured":"Kalantidis, Y., Sariyildiz, M.B., Pion, N., Weinzaepfel, P., Larlus, D.: Hard negative mixing for contrastive learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21798\u201321809 (2020)"},{"key":"24_CR27","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 26565\u201326577 (2022)"},{"key":"24_CR28","unstructured":"Kim, S., Lee, G., Bae, S., Yun, S.Y.: MixCo: mix-up contrastive learning for visual representation. arXiv preprint arXiv:2010.06300 (2020)"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Koohpayegani, S.A., Tejankar, A., Pirsiavash, H.: Mean shift for self-supervised learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10326\u201310335 (2021)","DOI":"10.1109\/ICCV48922.2021.01016"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"24_CR31","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"24_CR32","unstructured":"Lee, K., Zhu, Y., Sohn, K., Li, C.L., Shin, J., Lee, H.: $$ i $$-mix: a domain-agnostic strategy for contrastive representation learning. In: International Conference on Learning Representations (2020)"},{"key":"24_CR33","unstructured":"Li, T., Katabi, D., He, K.: Self-conditioned image generation via generating representations. arXiv preprint arXiv:2312.03701 (2023)"},{"key":"24_CR34","unstructured":"Ma, S., Zeng, Z., McDuff, D., Song, Y.: Active contrastive learning of audio-visual video representations. arXiv preprint arXiv:2009.09805 (2020)"},{"key":"24_CR35","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing, pp. 722\u2013729. IEEE (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"24_CR37","unstructured":"Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"24_CR38","doi-asserted-by":"crossref","unstructured":"Pan, T., Song, Y., Yang, T., Jiang, W., Liu, W.: VideoMoCo: contrastive video representation learning with temporally adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11205\u201311214 (2021)","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"24_CR39","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3498\u20133505. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Qian, R., et al.: Spatiotemporal contrastive video representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6964\u20136974 (2021)","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"24_CR41","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents, 1(2), 3. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"24_CR42","unstructured":"Robinson, J.D., Chuang, C.Y., Sra, S., Jegelka, S.: Contrastive learning with hard negative samples. In: International Conference on Learning Representations (2020)"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Shen, Z., Liu, Z., Liu, Z., Savvides, M., Darrell, T., Xing, E.: Un-Mix: rethinking image mixtures for unsupervised visual representation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2216\u20132224 (2022)","DOI":"10.1609\/aaai.v36i2.20119"},{"key":"24_CR45","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"24_CR46","unstructured":"Tabassum, A., Wahed, M., Eldardiry, H., Lourentzou, I.: Hard negative sampling strategies for contrastive representation learning. arXiv preprint arXiv:2206.01197 (2022)"},{"key":"24_CR47","unstructured":"Wang, R., Dai, X., et\u00a0al.: Contrastive learning-enhanced nearest neighbor mechanism for multi-label text classification. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 672\u2013679 (2022)"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Wu, Y., Wang, Z., Zeng, D., Shi, Y., Hu, J.: Synthetic data can also teach: synthesizing effective data for unsupervised visual representation learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 2866\u20132874 (2023)","DOI":"10.1609\/aaai.v37i3.25388"},{"key":"24_CR49","doi-asserted-by":"crossref","unstructured":"Xiang, W., Yang, H., Huang, D., Wang, Y.: Denoising diffusion autoencoders are unified self-supervised learners. arXiv preprint arXiv:2303.09769 (2023)","DOI":"10.1109\/ICCV51070.2023.01448"},{"key":"24_CR50","doi-asserted-by":"crossref","unstructured":"Xie, Z., Lin, Y., Zhang, Z., Cao, Y., Lin, S., Hu, H.: Propagate yourself: exploring pixel-level consistency for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16684\u201316693 (2021)","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"24_CR51","doi-asserted-by":"crossref","unstructured":"Yang, X., Wang, X.: Diffusion model as representation learner. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18938\u201318949 (2023)","DOI":"10.1109\/ICCV51070.2023.01736"},{"key":"24_CR52","doi-asserted-by":"crossref","unstructured":"Ye, S., Kim, J., Oh, A.H.: Efficient contrastive learning via novel data augmentation and curriculum learning. In: The 2021 Conference on Empirical Methods in Natural Language Processing. Empirical Methods in Natural Language Processing (EMNLP 2021) (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.138"},{"key":"24_CR53","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1007\/978-3-031-19809-0_38","volume-title":"ECCV 2022","author":"CH Yeh","year":"2022","unstructured":"Yeh, C.H., Hong, C.Y., Hsu, Y.C., Liu, T.L., Chen, Y., LeCun, Y.: Decoupled contrastive learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13686, pp. 668\u2013684. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_38"},{"key":"24_CR54","unstructured":"You, Y., Chen, T., Sui, Y., Chen, T., Wang, Z., Shen, Y.: Graph contrastive learning with augmentations. In: Advances in Neural Information Processing Systems, vol. 33, pp. 5812\u20135823 (2020)"},{"key":"24_CR55","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: self-supervised learning via redundancy reduction. In: International Conference on Machine Learning, pp. 12310\u201312320. PMLR (2021)"},{"key":"24_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/978-3-030-87196-3_21","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"D Zeng","year":"2021","unstructured":"Zeng, D., et al.: Positional contrastive learning for\u00a0volumetric medical image segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 221\u2013230. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87196-3_21"},{"key":"24_CR57","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018)"},{"key":"24_CR58","doi-asserted-by":"crossref","unstructured":"Zhu, R., Zhao, B., Liu, J., Sun, Z., Chen, C.W.: Improving contrastive learning by visualizing feature transformation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10306\u201310315 (2021)","DOI":"10.1109\/ICCV48922.2021.01014"}],"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\/978-3-031-72913-3_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:27:06Z","timestamp":1733095626000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72913-3_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031729126","9783031729133"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72913-3_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 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"}}]}}