mlsanityData to 7 Oct 2026

Integrating Prior Knowledge in Contrastive Learning with Kernel

arXiv 2206.01646 ↗First posted 3 Jun 2022cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Data augmentation is a crucial component in unsupervised contrastive learning (CL). It determines how positive samples are defined and, ultimately, the quality of the learned representation. In this work, we open the door to new perspectives for CL by integrating prior knowledge, given either by generative models -- viewed as prior representations -- or weak attributes in the positive and negative sampling. To this end, we use kernel theory to propose a novel loss, called decoupled uniformity, that i) allows the integration of prior knowledge and ii) removes the negative-positive coupling in the original InfoNCE loss. We draw a connection between contrastive learning and conditional mean embedding theory to derive tight bounds on the downstream classification loss. In an unsupervised setting, we empirically demonstrate that CL benefits from generative models to improve its representation both on natural and medical images. In a weakly supervised scenario, our framework outperforms other unconditional and conditional CL approaches.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 44 of its 62 references that are in the map. First posted on arXiv 3 Jun 2022.

Builds on

44 of 62 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2016Densely Connected Convolutional Networkscited by 6,691
  8. 2022Generative Adversarial Networkscited by 5,603
  9. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  10. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  11. 2020Supervised Contrastive Learningcited by 2,803
  12. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
32 more
  1. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  2. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  3. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  4. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  5. 2019Contrastive Multiview Codingcited by 1,297
  6. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  7. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 636
  8. 2019On Variational Bounds of Mutual Informationcited by 550
  9. 2019A Theoretical Analysis of Contrastive Unsupervised Representation Learningcited by 530
  10. 2017Large Batch Training of Convolutional Networkscited by 529
  11. 2019A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmarkcited by 419
  12. 2020Debiased Contrastive Learningcited by 354
  13. 2016Adversarial Feature Learningcited by 350
  14. 2020The Pitfalls of Simplicity Bias in Neural Networkscited by 349
  15. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 324
  16. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
  17. 2021Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Losscited by 311
  18. 2019Large Scale Adversarial Representation Learningcited by 238
  19. 2016Adversarially Learned Inferencecited by 216
  20. 2020Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biasescited by 143
  21. 2021Decoupled Contrastive Learningcited by 141
  22. 2020Intriguing Properties of Contrastive Lossescited by 129
  23. 2021Can contrastive learning avoid shortcut solutions?cited by 114
  24. 2022Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlapcited by 105
  25. 2021Generative Models as a Data Source for Multiview Representation Learningcited by 104
  26. 2022Understanding Contrastive Learning Requires Incorporating Inductive Biasescited by 96
  27. 2021ReSSL: Relational Self-Supervised Learning with Weak Augmentationcited by 83
  28. 2021Weakly Supervised Contrastive Learningcited by 81
  29. 2021Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classificationcited by 49
  30. 2019A Rigorous Theory of Conditional Mean Embeddingscited by 31
  31. 2022Conditional Contrastive Learning with Kernelcited by 22
  32. 2020Improving Transformation Invariance in Contrastive Representation Learningcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 2; 2026: 4.

11 papers.

  1. 2024Separating common from salient patterns with Contrastive Representation Learningcited by 6
  2. 2024Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Lossescited by 6
  3. 2025Your contrastive learning problem is secretly a distribution alignment problemcited by 6
  4. 2023Decoupled conditional contrastive learning with variable metadata for prostate lesion detectioncited by 2
  5. 2026Automatic Discovery of Disease Subgroups by Contrasting with Healthy Controlscited by 2
  6. 2024Unsupervised contrastive analysis for anomaly detection in brain MRIs via conditional diffusion modelscited by 1
  7. 2026Diff-CA: Separating Common and Salient Factors with Diffusion Modelscited by 1
  8. 2023Meta-Prior: Meta learning for Adaptive Inverse Problem Solverscited by 0
  9. 2025Robust brain age estimation from structural MRI with contrastive learningcited by 0
  10. 2026Contrastive Learning under Noisy Temporal Self-Supervision for Colonoscopy Videoscited by 0
  11. 2026Expressivity In Multimodal Contrastive Learningcited by 0