{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T04:08:59Z","timestamp":1784606939629,"version":"3.55.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T00:00:00Z","timestamp":1707955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T00:00:00Z","timestamp":1707955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Postgraduate Research & Practice Innovation Program of Jiangsu Province","award":["KYCX23_1065"],"award-info":[{"award-number":["KYCX23_1065"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906098"],"award-info":[{"award-number":["61906098"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Contrastive learning has emerged as an essential approach in self-supervised visual representation learning. Its main goal is to maximize the similarities between augmented versions of the same image (positive pairs), while minimizing the similarities between different images (negative pairs). Recent studies have demonstrated that harder negative samples, i.e., those that are more challenging to differentiate from the anchor sample perform a more crucial function in contrastive learning. However, many existing contrastive learning methods ignore the role of hard negative samples. In order to provide harder negative samples for the network model more efficiently. This paper proposes a novel feature-level sample sampling method, namely sampling synthetic hard negative samples for contrastive learning (SSCL). Specifically, we generate more and harder negative samples by mixing them through linear combination and ensure their reliability by debiasing. Finally, we execute weighted sampling of these negative samples. Compared to state-of-the-art methods, our method can provide more high-quality negative samples. Experiments show that SSCL improves the classification performance on different image datasets and can be readily integrated into existing methods.<\/jats:p>","DOI":"10.1007\/s11063-024-11522-2","type":"journal-article","created":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T02:02:08Z","timestamp":1707962528000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Synthetic Hard Negative Samples for Contrastive Learning"],"prefix":"10.1007","volume":"56","author":[{"given":"Hengkui","family":"Dong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianzhong","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,15]]},"reference":[{"key":"11522_CR1","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International conference on machine learning, pp 1597\u20131607"},{"key":"11522_CR2","doi-asserted-by":"crossref","unstructured":"He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: IEEE conference on computer vision and pattern recognition, pp 9729\u20139738","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"11522_CR3","unstructured":"Chen X, Fan H, Girshick R, He K (2020) Improved baselines with momentum contrastive learning arXiv:2003.04297"},{"key":"11522_CR4","unstructured":"Cai TT, Frankle J, Schwab DJ, Morcos AS (2020) Are all negatives created equal in contrastive instance discrimination? arXiv:2010.06682"},{"key":"11522_CR5","doi-asserted-by":"crossref","unstructured":"Dwibedi D, Aytar Y, Tompson J, Sermanet P, Zisserman A (2021) With a little help from my friends: nearest-neighbor contrastive learning of visual representations. In: IEEE\/CVF international conference on computer vision, pp 9588\u20139597","DOI":"10.1109\/ICCV48922.2021.00945"},{"key":"11522_CR6","unstructured":"Azabou M, Azar MG, Liu R, Lin C-H, Johnson EC, Bhaskaran-Nair K, Dabagia M, Avila-Pires B, Kitchell L, Hengen KB, et al (2021) Mine your own view: self-supervised learning through across-sample prediction. arXiv:2102.10106"},{"key":"11522_CR7","unstructured":"Caron M, Misra I, Mairal J, Goyal P, Bojanowski P, Joulin A (2020) Unsupervised learning of visual features by contrasting cluster assignments. In: Advances in neural information processing systems, pp 9912\u20139924"},{"key":"11522_CR8","unstructured":"Grill J-B, Strub F, Altch\u00e9 F, Tallec C, Richemond P, Buchatskaya E, Doersch C, Avila\u00a0Pires B, Guo Z, Gheshlaghi\u00a0Azar M et al (2020) Bootstrap your own latent-a new approach to self-supervised learning. In: Advances in neural information processing systems, pp 21271\u201321284"},{"key":"11522_CR9","doi-asserted-by":"crossref","unstructured":"Chen X, He K (2021) Exploring simple siamese representation learning. In: IEEE conference on computer vision and pattern recognition, pp 15750\u201315758","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"11522_CR10","unstructured":"Kim S, Lee G, Bae S, Yun S-Y (2020) Mixco: mix-up contrastive learning for visual representation. arXiv:2010.06300"},{"key":"11522_CR11","doi-asserted-by":"crossref","unstructured":"Shen Z, Liu Z, Liu Z, Savvides M, Darrell T, Xing E (2022) Un-mix: rethinking image mixtures for unsupervised visual representation learning. In: The AAAI conference on artificial intelligence, pp 2216\u20132224","DOI":"10.1609\/aaai.v36i2.20119"},{"key":"11522_CR12","unstructured":"Biswas M, Buckchash H, Prasad DK (2023) pnnclr: stochastic pseudo neighborhoods for contrastive learning based unsupervised representation learning problems. arXiv:2308.06983"},{"key":"11522_CR13","unstructured":"Chongjian G, Wang J, Tong Z, Chen S, Song Y, Luo P (2023) Soft neighbors are positive supporters in contrastive visual representation learning. In: International conference on learning representations"},{"key":"11522_CR14","unstructured":"Kalantidis Y, Sariyildiz MB, Pion N, Weinzaepfel P, Larlus D (2020) Hard negative mixing for contrastive learning. In: Advances in neural information processing systems, pp 21798\u201321809"},{"key":"11522_CR15","unstructured":"Zhu W, Shang H, Lv T, Liao C, Yang S, Liu J (2022) Adversarial contrastive self-supervised learning. arXiv:2202.13072"},{"key":"11522_CR16","doi-asserted-by":"crossref","unstructured":"Hu Q, Wang X, Hu W, Qi G-J (2021) Adco: adversarial contrast for efficient learning of unsupervised representations from self-trained negative adversaries. In: IEEE conference on computer vision and pattern recognition, pp 1074\u20131083","DOI":"10.1109\/CVPR46437.2021.00113"},{"key":"11522_CR17","unstructured":"Chuang C-Y, Robinson J, Lin Y-C, Torralba A, Jegelka S (2020) Debiased contrastive learning. In: Advances in neural information processing systems, pp 8765\u20138775"},{"key":"11522_CR18","unstructured":"Robinson J, Chuang C-Y, Sra S, Jegelka S (2021) Contrastive learning with hard negative samples. In: international conference on learning representations, pp 1\u201329"},{"key":"11522_CR19","unstructured":"Liu B, Wang B (2023) Bayesian self-supervised contrastive learning. arXiv:2301.11673"},{"key":"11522_CR20","unstructured":"Du\u00a0Plessis MC, Niu G, Sugiyama M (2014) Analysis of learning from positive and unlabeled data. In: Advances in neural information processing systems, pp 703\u2013711"},{"key":"11522_CR21","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 computer society conference on computer vision and pattern, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11522_CR22","unstructured":"Krizhevsky A, Hinton G et al (2009) Learning multiple layers of features from tiny images, pp 1\u201360"},{"issue":"7","key":"11522_CR23","first-page":"3","volume":"7","author":"Y Le","year":"2015","unstructured":"Le Y, Yang X (2015) Tiny imagenet visual recognition challenge. CS 231N 7(7):3","journal-title":"CS 231N"},{"key":"11522_CR24","unstructured":"Coates A, Ng A, Lee H (2011) 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"},{"key":"11522_CR25","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"11522_CR26","doi-asserted-by":"crossref","unstructured":"Wu Z, Xiong Y, Yu SX, Lin D (2018) Unsupervised feature learning via non-parametric instance discrimination. In: IEEE conference on computer vision and pattern recognition, pp 3733\u20133742","DOI":"10.1109\/CVPR.2018.00393"},{"issue":"11","key":"11522_CR27","first-page":"2579","volume":"9","author":"L Maaten","year":"2008","unstructured":"Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(11):2579\u20132605","journal-title":"J Mach Learn Res"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11522-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-024-11522-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11522-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T20:14:51Z","timestamp":1709237691000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-024-11522-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,15]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["11522"],"URL":"https:\/\/doi.org\/10.1007\/s11063-024-11522-2","relation":{},"ISSN":["1573-773X"],"issn-type":[{"value":"1573-773X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,15]]},"assertion":[{"value":"3 January 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"33"}}