mlsanityData to 7 Oct 2026

Class-Aware Contrastive Semi-Supervised Learning

arXiv 2203.02261 ↗First posted 4 Mar 2022cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover, the model's judgment becomes noisier in real-world applications with extensive out-of-distribution data. To address this issue, we propose a general method named Class-aware Contrastive Semi-Supervised Learning (CCSSL), which is a drop-in helper to improve the pseudo-label quality and enhance the model's robustness in the real-world setting. Rather than treating real-world data as a union set, our method separately handles reliable in-distribution data with class-wise clustering for blending into downstream tasks and noisy out-of-distribution data with image-wise contrastive for better generalization. Furthermore, by applying target re-weighting, we successfully emphasize clean label learning and simultaneously reduce noisy label learning. Despite its simplicity, our proposed CCSSL has significant performance improvements over the state-of-the-art SSL methods on the standard datasets CIFAR100 and STL10. On the real-world dataset Semi-iNat 2021, we improve FixMatch by 9.80% and CoMatch by 3.18%. Code is available https://github.com/TencentYoutuResearch/Classification-SemiCLS.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). Builds on 24 of its 34 references that are in the map. First posted on arXiv 4 Mar 2022.

Builds on

24 of 34 references.

References · 24

  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. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  7. 2020Supervised Contrastive Learningcited by 2,803
  8. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  9. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  10. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  11. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 507
  12. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
12 more
  1. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  2. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  3. 2019Label Propagation for Deep Semi-supervised Learningcited by 287
  4. 2020CoMatch: Semi-supervised Learning with Contrastive Graph Regularizationcited by 167
  5. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
  6. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 115
  7. 2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 112
  8. 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
  9. 2021Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detectioncited by 48
  10. 2021A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classificationcited by 36
  11. 2021All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-trainingcited by 32
  12. 2021The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshopcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 22; 2024: 18; 2025: 10; 2026: 4.

62 papers.

Sort:

By area:

  1. 2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
  2. 2022OpenCon: Open-world Contrastive Learningcited by 33
  3. 2022Instance-specific and Model-adaptive Supervision for Semi-supervised Semantic Segmentationcited by 30
  4. 2024M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoisingcited by 24
  5. 2023A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learningcited by 22
  6. 2023Semi-supervised learning made simple with self-supervised clusteringcited by 20
  7. 2024Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learningcited by 19
  8. 2023Rethinking Weak Supervision in Helping Contrastive Learningcited by 18
  9. 2023Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learningcited by 17
  10. 2022Label-Efficient Online Continual Object Detection in Streaming Videocited by 16
  11. 2023InstanT: Semi-supervised Learning with Instance-dependent Thresholdscited by 13
  12. 2023SimMatchV2: Semi-Supervised Learning with Graph Consistencycited by 12
38 more
  1. 2023Towards Semi-supervised Learning with Non-random Missing Labelscited by 12
  2. 2022Semi-Supervised Semantic Segmentation with Cross Teacher Trainingcited by 11
  3. 2023RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Datacited by 10
  4. 2023Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatchcited by 8
  5. 2023Semi-Supervised Semantic Segmentation via Marginal Contextual Informationcited by 8
  6. 2022MultiMatch: Multi-task Learning for Semi-supervised Domain Generalizationcited by 7
  7. 2024SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentationcited by 7
  8. 2023Improving Open-Set Semi-Supervised Learning with Self-Supervisioncited by 6
  9. 2022Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertaintycited by 5
  10. 2022Boosting Semi-Supervised Learning with Contrastive Complementary Labelingcited by 5
  11. 2026QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restorationcited by 5
  12. 2023Multi-Scale Cross Contrastive Learning for Semi-Supervised Medical Image Segmentationcited by 4
  13. 2022Dual Class-Aware Contrastive Federated Semi-Supervised Learningcited by 3
  14. 2023GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergencecited by 3
  15. 2023SINCERE: Supervised Information Noise-Contrastive Estimation REvisitedcited by 3
  16. 2024Robust Semi-supervised Learning via f-Divergence and α-R'enyi Divergencecited by 3
  17. 2024ProSub: Probabilistic Open-Set Semi-Supervised Learning with Subspace-Based Out-of-Distribution Detectioncited by 3
  18. 2024FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognitioncited by 3
  19. 2023Enhancing Self-Training Methodscited by 2
  20. 2023Semi-Supervised and Long-Tailed Object Detection with CascadeMatchcited by 2
  21. 2023Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Datacited by 2
  22. 2023Semi-Supervised End-To-End Contrastive Learning For Time Series Classificationcited by 2
  23. 2023Debiasing, calibrating, and improving Semi-supervised Learning performance via simple Ensemble Projectorcited by 2
  24. 2024Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learningcited by 2
  25. 2024Semi-Supervised Unconstrained Head Pose Estimation in the Wildcited by 2
  26. 2024PEPL: Precision-Enhanced Pseudo-Labeling for Fine-Grained Image Classification in Semi-Supervised Learningcited by 2
  27. 2025An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noisecited by 2
  28. 2025Unsupervised Learning for Class Distribution Mismatchcited by 2
  29. 2025Exemplar Med-DETR: Toward Generalized and Robust Lesion Detection in Mammogram Images and beyondcited by 2
  30. 2025Robust Learning of Diffusion Models with Extremely Noisy Conditionscited by 2
  31. 2026Towards Multimodal Domain Generalization with Few Labelscited by 2
  32. 2023ContrasInver: Ultra-Sparse Label Semi-supervised Regression for Multi-dimensional Seismic Inversioncited by 1
  33. 2023LiT Tuned Models for Efficient Species Detectioncited by 1
  34. 2024Open-World Semi-Supervised Learning for Node Classificationcited by 1
  35. 2024A Method of Moments Embedding Constraint and its Application to Semi-Supervised Learningcited by 1
  36. 2024Towards Adaptive Pseudo-label Learning for Semi-Supervised Temporal Action Localizationcited by 1
  37. 2024Bridging the Gaps: Utilizing Unlabeled Face Recognition Datasets to Boost Semi-Supervised Facial Expression Recognitioncited by 1
  38. 2023CLAF: Contrastive Learning with Augmented Features for Imbalanced Semi-Supervised Learningcited by 0

50 most cited of 62 All 62 (JSON)