mlsanityData to 7 Oct 2026

A Framework For Contrastive Self-Supervised Learning And Designing A New Approach

arXiv 2009.00104 ↗First posted 31 Aug 2020cs.CV cs.LGcited by 51

Not on the map. Why?

Abstract (arXiv)

Contrastive self-supervised learning (CSL) is an approach to learn useful representations by solving a pretext task that selects and compares anchor, negative and positive (APN) features from an unlabeled dataset. We present a conceptual framework that characterizes CSL approaches in five aspects (1) data augmentation pipeline, (2) encoder selection, (3) representation extraction, (4) similarity measure, and (5) loss function. We analyze three leading CSL approaches--AMDIM, CPC, and SimCLR--, and show that despite different motivations, they are special cases under this framework. We show the utility of our framework by designing Yet Another DIM (YADIM) which achieves competitive results on CIFAR-10, STL-10 and ImageNet, and is more robust to the choice of encoder and the representation extraction strategy. To support ongoing CSL research, we release the PyTorch implementation of this conceptual framework along with standardized implementations of AMDIM, CPC (V2), SimCLR, BYOL, Moco (V2) and YADIM.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 17; 2022: 22; 2023: 6; 2024: 5; 2025: 1.

51 papers.

Sort:

By area:

  1. 2022What to Hide from Your Students: Attention-Guided Masked Image Modelingcited by 117
  2. 2021SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learningcited by 101
  3. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 97
  4. 2021Self-supervised representation learning from 12-lead ECG datacited by 80
  5. 2022A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributescited by 56
  6. 2022Neural Causal Models for Counterfactual Identification and Estimationcited by 54
  7. 2021Variational Wasserstein gradient flowcited by 53
  8. 2022Robust Contrastive Learning against Noisy Viewscited by 45
  9. 2022Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learningcited by 40
  10. 2022EM-driven unsupervised learning for efficient motion segmentationcited by 33
  11. 2021Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learningcited by 22
  12. 2024Counterfactual Image Editingcited by 20
38 more
  1. 2021Latent Structure Mining with Contrastive Modality Fusion for Multimedia Recommendationcited by 18
  2. 2023A Survey on Semi-Supervised Semantic Segmentationcited by 16
  3. 2022The Robustness Limits of SoTA Vision Models to Natural Variationcited by 15
  4. 2025Learn Beneficial Noise as Graph Augmentationcited by 15
  5. 2021Learning Representations with Contrastive Self-Supervised Learning for Histopathology Applicationscited by 12
  6. 2021RELAX: Representation Learning Explainabilitycited by 12
  7. 2021Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddingscited by 11
  8. 2024CAMBranch: Contrastive Learning with Augmented MILPs for Branchingcited by 10
  9. 2022Tools and Practices for Responsible AI Engineeringcited by 9
  10. 2022Deep Learning-based Framework for Automatic Cranial Defect Reconstruction and Implant Modelingcited by 8
  11. 2022TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervisioncited by 8
  12. 2021Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representationcited by 7
  13. 2021Sensor Data Augmentation by Resampling for Contrastive Learning in Human Activity Recognitioncited by 7
  14. 2021Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categoriescited by 7
  15. 2021Recur, Attend or Convolve? On Whether Temporal Modeling Matters for Cross-Domain Robustness in Action Recognitioncited by 7
  16. 2023In-Distribution and Out-of-Distribution Self-supervised ECG Representation Learning for Arrhythmia Detectioncited by 7
  17. 2021Cross-Lingual Open-Domain Question Answering with Answer Sentence Generationcited by 6
  18. 2021A Framework using Contrastive Learning for Classification with Noisy Labelscited by 5
  19. 2022Negative Selection by Clustering for Contrastive Learning in Human Activity Recognitioncited by 5
  20. 2022Unsupervised Method for Intra-patient Registration of Brain Magnetic Resonance Images based on Objective Function Weighting by Inverse Consistency: Contribution to the BraTS-Reg Challengecited by 5
  21. 2022Improving Classification Model Performance on Chest X-Rays through Lung Segmentationcited by 4
  22. 2022enpheeph: A Fault Injection Framework for Spiking and Compressed Deep Neural Networkscited by 4
  23. 2022Distinguishing representational geometries with controversial stimuli: Bayesian experimental design and its application to face dissimilarity judgmentscited by 4
  24. 2023Self-Supervised In-Domain Representation Learning for Remote Sensing Image Scene Classificationcited by 4
  25. 2021Improving Compositionality of Neural Networks by Decoding Representations to Inputscited by 2
  26. 2022Time-based Self-supervised Learning for Wireless Capsule Endoscopycited by 2
  27. 2022Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garmentcited by 2
  28. 2021AASAE: Augmentation-Augmented Stochastic Autoencoderscited by 1
  29. 2022SubOmiEmbed: Self-supervised Representation Learning of Multi-omics Data for Cancer Type Classificationcited by 1
  30. 2023ISimDL: Importance Sampling-Driven Acceleration of Fault Injection Simulations for Evaluating the Robustness of Deep Learningcited by 1
  31. 2022DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysiscited by 0
  32. 2022User Guide for KOTE: Korean Online Comments Emotions Datasetcited by 0
  33. 2022[Reproducibility Report] Path Planning using Neural A* Searchcited by 0
  34. 2022Interactive Visual Feature Searchcited by 0
  35. 2023Supervised and Contrastive Self-Supervised In-Domain Representation Learning for Dense Prediction Problems in Remote Sensingcited by 0
  36. 2023Prompt-Based Learning for Thread Structure Prediction in Cybersecurity Forumscited by 0
  37. 2024Exploiting Data Hierarchy as a New Modality for Contrastive Learningcited by 0
  38. 2024Improving Antibody Humanness Prediction using Patent Datacited by 0

50 most cited of 51 All 51 (JSON)