mlsanityData to 7 Oct 2026

Max-Margin Contrastive Learning

arXiv 2112.11450 ↗First posted 21 Dec 2021cs.LG cs.AI cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Standard contrastive learning approaches usually require a large number of negatives for effective unsupervised learning and often exhibit slow convergence. We suspect this behavior is due to the suboptimal selection of negatives used for offering contrast to the positives. We counter this difficulty by taking inspiration from support vector machines (SVMs) to present max-margin contrastive learning (MMCL). Our approach selects negatives as the sparse support vectors obtained via a quadratic optimization problem, and contrastiveness is enforced by maximizing the decision margin. As SVM optimization can be computationally demanding, especially in an end-to-end setting, we present simplifications that alleviate the computational burden. We validate our approach on standard vision benchmark datasets, demonstrating better performance in unsupervised representation learning over state-of-the-art, while having better empirical convergence properties.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 46 of its 67 references that are in the map. First posted on arXiv 21 Dec 2021.

Builds on

46 of 67 references.

References · 46

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  5. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  6. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  8. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  9. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  10. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
  11. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  12. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
34 more
  1. 2019Contrastive Multiview Codingcited by 1,297
  2. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  3. 2016Colorful Image Colorizationcited by 1,113
  4. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  5. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  6. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  7. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 806
  8. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 657
  9. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
  10. 2020Contrastive Learning with Hard Negative Samplescited by 619
  11. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 588
  12. 2019A Theoretical Analysis of Contrastive Unsupervised Representation Learningcited by 530
  13. 2017Large Batch Training of Convolutional Networkscited by 529
  14. 2017Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classificationcited by 521
  15. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  16. 2020Hard Negative Mixing for Contrastive Learningcited by 399
  17. 2020Debiased Contrastive Learningcited by 354
  18. 2016Learning Representations for Automatic Colorizationcited by 251
  19. 2020Self-supervised Co-training for Video Representation Learningcited by 232
  20. 2020What Should Not Be Contrastive in Contrastive Learningcited by 224
  21. 2017Unsupervised Representation Learning by Sorting Sequencescited by 219
  22. 2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 216
  23. 2020How Well Do Self-Supervised Models Transfer?cited by 213
  24. 2019Local Aggregation for Unsupervised Learning of Visual Embeddingscited by 204
  25. 2018An efficient framework for learning sentence representationscited by 197
  26. 2020Contrastive Learning of General-Purpose Audio Representationscited by 168
  27. 2020Boosting Contrastive Self-Supervised Learning with False Negative Cancellationcited by 119
  28. 2016On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimizationcited by 108
  29. 2020Online Deep Clustering for Unsupervised Representation Learningcited by 99
  30. 2019AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Datacited by 77
  31. 2018Mining on Manifolds: Metric Learning without Labelscited by 36
  32. 2018Stochastic Negative Mining for Learning with Large Output Spacescited by 29
  33. 2019GPU Acceleration of ADMM for Large-Scale Quadratic Programmingcited by 15
  34. 2018Video Representation Learning Using Discriminative Poolingcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 8; 2024: 7; 2025: 6; 2026: 3.

27 papers.

Sort:

By area:

  1. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  2. 2023HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actionscited by 25
  3. 2022VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignmentcited by 20
  4. 2024Emergent Visual-Semantic Hierarchies in Image-Text Representationscited by 19
  5. 2023Hallucination Improves the Performance of Unsupervised Visual Representation Learningcited by 16
  6. 2022Hard Negative Sampling Strategies for Contrastive Representation Learningcited by 13
  7. 2023STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videoscited by 13
  8. 2023Learning by Sorting: Self-supervised Learning with Group Ordering Constraintscited by 13
  9. 2022Model-Aware Contrastive Learning: Towards Escaping the Dilemmascited by 11
  10. 2025CLOC: Contrastive Learning for Ordinal Classification with Multi-Margin N-pair Losscited by 11
  11. 2024Understanding Hyperbolic Metric Learning through Hard Negative Samplingcited by 10
  12. 2024Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learningcited by 9
15 more
  1. 2024Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse Reinforcement Learningcited by 5
  2. 2025An Augmentation Overlap Theory of Contrastive Learningcited by 5
  3. 2023Distortion-Disentangled Contrastive Learningcited by 4
  4. 2023Representation Learning Dynamics of Self-Supervised Modelscited by 3
  5. 2024ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in Videoscited by 3
  6. 2024ConPro: Learning Severity Representation for Medical Images using Contrastive Learning and Preference Optimizationcited by 3
  7. 2025Assessing the Completeness of Traffic Scenario Categories for Automated Highway Driving Functions via Cluster-based Analysiscited by 3
  8. 2025SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector Regularizationcited by 3
  9. 2023Erasing Self-Supervised Learning Backdoor by Cluster Activation Maskingcited by 1
  10. 2024When can we Approximate Wide Contrastive Models with Neural Tangent Kernels and Principal Component Analysis?cited by 1
  11. 2025SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classificationcited by 1
  12. 2025Discovering Global False Negatives On the Fly for Self-supervised Contrastive Learningcited by 0
  13. 2026MedSAD-CLIP: Supervised CLIP with Token-Patch Cross-Attention for Medical Anomaly Detection and Segmentationcited by 0
  14. 2026ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margincited by 0
  15. 2026Fusion is not one-size-fits-all: Cross-Modal Representation Alignment for Time-to-Event Modelingcited by 0