{"url":"/task/contrastive-learning","name":"Contrastive Learning","slug":"contrastive-learning","description_markdown":"**Contrastive Learning** is a deep learning technique for unsupervised representation learning. The goal is to learn a representation of data such that similar instances are close together in the representation space, while dissimilar instances are far apart.\r\n\r\nIt has been shown to be effective in various computer vision and natural language processing tasks, including image retrieval, zero-shot learning, and cross-modal retrieval. In these tasks, the learned representations can be used as features for downstream tasks such as classification and clustering.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">(Image credit: [Schroff et al. 2015](https://arxiv.org/abs/1503.03832))</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":6661,"papers_with_code":3104,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":16,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/contrastive-learning-on-imagenet-1k","slug":"contrastive-learning-on-imagenet-1k","dataset":"imagenet-1k","dataset_url":"/dataset/imagenet","rows_in_archive":14,"metrics":["ImageNet Top-1 Accuracy"],"first_row_in_archive_order":{"model":"ResNet50","paper_title":"Matrix Information Theory for Self-Supervised Learning","paper_url":"/paper/kernel-ssl-kernel-kl-divergence-for-self","paper_date":"2023-05-27","arxiv_id":"2305.17326","code_links":[{"title":"yifanzhang-pro/matrix-ssl","url":"https://github.com/yifanzhang-pro/matrix-ssl"},{"title":"yifanzhang-pro/matrix-llm","url":"https://github.com/yifanzhang-pro/matrix-llm"},{"title":"huang-research-group/Matrix-SSL","url":"https://github.com/huang-research-group/Matrix-SSL"}],"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}}},{"leaderboard":"/sota/contrastive-learning-on-10000-people-human","slug":"contrastive-learning-on-10000-people-human","dataset":"10,000 People - Human Pose Recognition Data","dataset_url":"/dataset/10000-people-human-pose-recognition-data","rows_in_archive":1,"metrics":["0..5sec"],"first_row_in_archive_order":{"model":"1","paper_title":"DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning","paper_url":"/paper/decisionnce-embodied-multimodal","paper_date":"2024-02-28","arxiv_id":"2402.18137","code_links":[{"title":"2toinf/DecisionNCE","url":"https://github.com/2toinf/DecisionNCE"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/contrastive-learning-on-cifar-10","slug":"contrastive-learning-on-cifar-10","dataset":"CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":1,"metrics":["Accuracy (Top-1)"],"first_row_in_archive_order":{"model":"IPCL (ResNet18)","paper_title":"IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation","paper_url":"/paper/ipcl-iterative-pseudo-supervised-contrastive","paper_date":"2024-03-18","arxiv_id":null,"code_links":[{"title":"SonalKumar95/IPCL","url":"https://github.com/SonalKumar95/IPCL"}],"syntology":null}},{"leaderboard":"/sota/contrastive-learning-on-stl-10","slug":"contrastive-learning-on-stl-10","dataset":"STL-10","dataset_url":"/dataset/stl-10","rows_in_archive":1,"metrics":["Accuracy (Top-1)"],"first_row_in_archive_order":{"model":"IPCL (ResNet18)","paper_title":"IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation","paper_url":"/paper/ipcl-iterative-pseudo-supervised-contrastive","paper_date":"2024-03-18","arxiv_id":null,"code_links":[{"title":"SonalKumar95/IPCL","url":"https://github.com/SonalKumar95/IPCL"}],"syntology":null}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/imagenet","name":"ImageNet","full_name":"","num_papers_in_archive":15430},{"url":"/dataset/stl-10","name":"STL-10","full_name":"Self-Taught Learning 10","num_papers_in_archive":1092},{"url":"/dataset/10000-people-human-pose-recognition-data","name":"10,000 People - Human Pose Recognition Data","full_name":"10,000 People - Human Pose Recognition Data","num_papers_in_archive":265},{"url":"/dataset/fsd50k","name":"FSD50K","full_name":"Freesound Database 50K","num_papers_in_archive":155},{"url":"/dataset/guitarset","name":"GuitarSet","full_name":null,"num_papers_in_archive":31},{"url":"/dataset/inria-aerial-image-labeling","name":"INRIA Aerial Image Labeling","full_name":"INRIA Aerial Image Labeling","num_papers_in_archive":21},{"url":"/dataset/fivr-200k","name":"FIVR-200K","full_name":"","num_papers_in_archive":16},{"url":"/dataset/olives-dataset","name":"OLIVES Dataset","full_name":"Ophthalmic Labels for Investigating Visual Eye Semantics","num_papers_in_archive":10},{"url":"/dataset/dad","name":"DAD","full_name":"Driver Anomaly Detection","num_papers_in_archive":9},{"url":"/dataset/bioscan-5m","name":"BIOSCAN-5M","full_name":"","num_papers_in_archive":4},{"url":"/dataset/commitbart","name":"CommitBART","full_name":"","num_papers_in_archive":3},{"url":"/dataset/us-4","name":"US-4","full_name":null,"num_papers_in_archive":3},{"url":"/dataset/extended-agriculture-vision","name":"Extended Agriculture-Vision","full_name":"","num_papers_in_archive":2},{"url":"/dataset/banknote-net","name":"BankNote-Net","full_name":"","num_papers_in_archive":1},{"url":"/dataset/matsim","name":"MatSim","full_name":"MatSim dataset for materials similarity recognition from images","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":3104,"tagged_in_all":6661,"items":[{"url":"/paper/a-simple-framework-for-contrastive-learning","title":"A Simple Framework for Contrastive Learning of Visual Representations","date":"2020-02-13","arxiv_id":"2002.05709","repositories_listed":96,"syntology":{"n":137,"n_ran":79,"n_unverified":58,"n_pointer_only":52}},{"url":"/paper/momentum-contrast-for-unsupervised-visual","title":"Momentum Contrast for Unsupervised Visual Representation Learning","date":"2019-11-13","arxiv_id":"1911.05722","repositories_listed":44,"syntology":{"n":42,"n_ran":26,"n_unverified":16,"n_pointer_only":16}},{"url":"/paper/improved-baselines-with-momentum-contrastive","title":"Improved Baselines with Momentum Contrastive Learning","date":"2020-03-09","arxiv_id":"2003.04297","repositories_listed":36,"syntology":{"n":43,"n_ran":8,"n_unverified":35,"n_pointer_only":10}},{"url":"/paper/supervised-contrastive-learning","title":"Supervised Contrastive Learning","date":"2020-04-23","arxiv_id":"2004.11362","repositories_listed":26,"syntology":{"n":23,"n_ran":6,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/simcse-simple-contrastive-learning-of","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","date":"2021-04-18","arxiv_id":"2104.08821","repositories_listed":23,"syntology":{"n":30,"n_ran":17,"n_unverified":13,"n_pointer_only":19}},{"url":"/paper/unsupervised-learning-of-visual-features-by","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","date":"2020-06-17","arxiv_id":"2006.09882","repositories_listed":18,"syntology":{"n":17,"n_ran":13,"n_unverified":4,"n_pointer_only":6}},{"url":"/paper/unsupervised-feature-learning-via-non","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","date":"2018-05-05","arxiv_id":"1805.01978","repositories_listed":15,"syntology":{"n":23,"n_ran":19,"n_unverified":4,"n_pointer_only":16}},{"url":"/paper/sigmoid-loss-for-language-image-pre-training","title":"Sigmoid Loss for Language Image Pre-Training","date":"2023-03-27","arxiv_id":"2303.15343","repositories_listed":11,"syntology":{"n":29,"n_ran":12,"n_unverified":17,"n_pointer_only":25}},{"url":"/paper/contrastive-learning-for-compact-single-image","title":"Contrastive Learning for Compact Single Image Dehazing","date":"2021-04-19","arxiv_id":"2104.09367","repositories_listed":10,"syntology":null},{"url":"/paper/contrastive-learning-for-unpaired-image-to","title":"Contrastive Learning for Unpaired Image-to-Image Translation","date":"2020-07-30","arxiv_id":"2007.15651","repositories_listed":10,"syntology":{"n":9,"n_ran":9,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/contrastive-multiview-coding","title":"Contrastive Multiview Coding","date":"2019-06-13","arxiv_id":"1906.05849","repositories_listed":8,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/scaling-deep-contrastive-learning-batch-size","title":"Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup","date":"2021-01-18","arxiv_id":"2101.06983","repositories_listed":7,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/propagate-yourself-exploring-pixel-level","title":"Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning","date":"2020-11-19","arxiv_id":"2011.10043","repositories_listed":7,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/dense-contrastive-learning-for-self","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","date":"2020-11-18","arxiv_id":"2011.09157","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/contrastive-learning-of-medical-visual","title":"Contrastive Learning of Medical Visual Representations from Paired Images and Text","date":"2020-10-02","arxiv_id":"2010.00747","repositories_listed":7,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/curl-contrastive-unsupervised-representations","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","date":"2020-04-08","arxiv_id":"2004.04136","repositories_listed":7,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/self-supervised-learning-of-pretext-invariant","title":"Self-Supervised Learning of Pretext-Invariant Representations","date":"2019-12-04","arxiv_id":"1912.01991","repositories_listed":7,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/languagebind-extending-video-language","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","date":"2023-10-03","arxiv_id":"2310.01852","repositories_listed":6,"syntology":{"n":14,"n_ran":7,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/towards-unsupervised-dense-information","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","date":"2021-12-16","arxiv_id":"2112.09118","repositories_listed":6,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/model-contrastive-federated-learning","title":"Model-Contrastive Federated Learning","date":"2021-03-30","arxiv_id":"2103.16257","repositories_listed":6,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/pre-trained-image-processing-transformer","title":"Pre-Trained Image Processing Transformer","date":"2020-12-01","arxiv_id":"2012.00364","repositories_listed":6,"syntology":null},{"url":"/paper/hyperspherical-consistency-regularization","title":"Hyperspherical Consistency Regularization","date":"2022-06-02","arxiv_id":"2206.00845","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/revisiting-3d-resnets-for-video-recognition","title":"Revisiting 3D ResNets for Video Recognition","date":"2021-09-03","arxiv_id":"2109.01696","repositories_listed":5,"syntology":null},{"url":"/paper/parametric-contrastive-learning","title":"Parametric Contrastive Learning","date":"2021-07-26","arxiv_id":"2107.12028","repositories_listed":5,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/rethinking-self-supervised-correspondence","title":"Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective","date":"2021-03-31","arxiv_id":"2103.17263","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/approximate-nearest-neighbor-negative","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","date":"2020-07-01","arxiv_id":"2007.00808","repositories_listed":5,"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/on-contrastive-learning-for-likelihood-free","title":"On Contrastive Learning for Likelihood-free Inference","date":"2020-02-10","arxiv_id":"2002.03712","repositories_listed":5,"syntology":null},{"url":"/paper/self-labelling-via-simultaneous-clustering-1","title":"Self-labelling via simultaneous clustering and representation learning","date":"2019-11-13","arxiv_id":"1911.05371","repositories_listed":5,"syntology":{"n":18,"n_ran":7,"n_unverified":11,"n_pointer_only":3}},{"url":"/paper/bioscan-clip-bridging-vision-and-genomics-for","title":"CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale","date":"2024-05-27","arxiv_id":"2405.17537","repositories_listed":4,"syntology":{"n":12,"n_ran":4,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/decoding-natural-images-from-eeg-for-object","title":"Decoding Natural Images from EEG for Object Recognition","date":"2023-08-25","arxiv_id":"2308.13234","repositories_listed":4,"syntology":{"n":12,"n_ran":7,"n_unverified":5,"n_pointer_only":0}}],"syntology_records":26,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}