mlsanityData to 7 Oct 2026

Generalized Parametric Contrastive Learning

arXiv 2209.12400 ↗First posted 26 Sep 2022cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose the Generalized Parametric Contrastive Learning (GPaCo/PaCo) which works well on both imbalanced and balanced data. Based on theoretical analysis, we observe that supervised contrastive loss tends to bias high-frequency classes and thus increases the difficulty of imbalanced learning. We introduce a set of parametric class-wise learnable centers to rebalance from an optimization perspective. Further, we analyze our GPaCo/PaCo loss under a balanced setting. Our analysis demonstrates that GPaCo/PaCo can adaptively enhance the intensity of pushing samples of the same class close as more samples are pulled together with their corresponding centers and benefit hard example learning. Experiments on long-tailed benchmarks manifest the new state-of-the-art for long-tailed recognition. On full ImageNet, models from CNNs to vision transformers trained with GPaCo loss show better generalization performance and stronger robustness compared with MAE models. Moreover, GPaCo can be applied to the semantic segmentation task and obvious improvements are observed on the 4 most popular benchmarks. Our code is available at https://github.com/dvlab-research/Parametric-Contrastive-Learning.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Builds on 54 of its 71 references that are in the map. First posted on arXiv 26 Sep 2022.

Builds on

54 of 71 references.

References · 54

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  8. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  9. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  10. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  11. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  12. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
38 more
  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  2. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  3. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  4. 2020Supervised Contrastive Learningcited by 2,803
  5. 2016Pyramid Scene Parsing Networkcited by 2,472
  6. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  7. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  8. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  9. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  10. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  11. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  12. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  13. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  14. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  15. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  16. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  17. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  18. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  19. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  20. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  21. 2018Path Aggregation Network for Instance Segmentationcited by 796
  22. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  23. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  24. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  25. 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
  26. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  27. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  28. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  29. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 270
  30. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  31. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 250
  32. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  33. 2020Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspectivecited by 143
  34. 2015Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networkscited by 115
  35. 2021Contrastive Learning with Stronger Augmentationscited by 100
  36. 2018Benchmarking Neural Network Robustness to Common Corruptions and Surface Variationscited by 99
  37. 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
  38. 2018Deep Imbalanced Learning for Face Recognition and Attribute Predictioncited by 90

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 11; 2024: 13; 2025: 11; 2026: 10.

45 papers.

Sort:

By area:

  1. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  2. 2024Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentationcited by 61
  3. 2023Decoupled Kullback-Leibler Divergence Losscited by 58
  4. 2024Probabilistic Contrastive Learning for Long-Tailed Visual Recognitioncited by 42
  5. 2024Unified Language-driven Zero-shot Domain Adaptationcited by 30
  6. 2023Inducing Neural Collapse in Deep Long-tailed Learningcited by 28
  7. 2023Learning Context-aware Classifier for Semantic Segmentationcited by 23
  8. 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentationcited by 20
  9. 2023Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancementcited by 19
  10. 2024Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognitioncited by 15
  11. 2025Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Priorcited by 15
  12. 2025Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classificationcited by 14
33 more
  1. 2026FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Mergingcited by 14
  2. 2023When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence Systemcited by 13
  3. 2024Classes Are Not Equal: An Empirical Study on Image Recognition Fairnesscited by 10
  4. 2024ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learningcited by 10
  5. 2025Long-tailed Recognition with Model Rebalancingcited by 10
  6. 2023SCoRe: Submodular Combinatorial Representation Learningcited by 7
  7. 2023Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolboxcited by 6
  8. 2024Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentationcited by 6
  9. 2025Generalized Kullback-Leibler Divergence Losscited by 6
  10. 2024Text-guided Foundation Model Adaptation for Long-Tailed Medical Image Classificationcited by 5
  11. 2024Fractal Calibration for long-tailed object detectioncited by 5
  12. 2024Rethinking Positive Pairs in Contrastive Learningcited by 5
  13. 2025Variational Supervised Contrastive Learningcited by 5
  14. 2026Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLMcited by 4
  15. 2023Dual Compensation Residual Networks for Class Imbalanced Learningcited by 2
  16. 2025Empowering Vision Transformers with Multi-Scale Causal Intervention for Long-Tailed Image Classificationcited by 2
  17. 2025PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clusteringcited by 2
  18. 2023Balanced Supervised Contrastive Learning for Few-Shot Class-Incremental Learningcited by 1
  19. 2024Reviving Undersampling for Long-Tailed Learningcited by 1
  20. 2025Aligned Contrastive Loss for Long-Tailed Recognitioncited by 1
  21. 2025Generative Distribution Distillationcited by 1
  22. 2026SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognitioncited by 1
  23. 2026Equilibrium contrastive learning for imbalanced image classificationcited by 1
  24. 2026Multimodal Dataset Distillation via Phased Teacher Modelscited by 1
  25. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstractcited by 0
  26. 2024EntProp: High Entropy Propagation for Improving Accuracy and Robustnesscited by 0
  27. 2025BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understandingcited by 0
  28. 2025Intrinsic Dimensionality as a Model-Free Measure of Class Imbalancecited by 0
  29. 2026OSDTW: Optimal Shared Depth and Task Weighting for Long-Tailed Recognitioncited by 0
  30. 2026Class-frequency Guided Noise Schedule for Diffusion Modelscited by 0
  31. 2026DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decodingcited by 0
  32. 2026Generalised Balanced Softmax: A Finite-Data Perspective on Logit Adjustment for Long-Tailed Recognitioncited by 0
  33. 2026CLEAR: Class-wise Expert Aggregation with Structured Sampling for Long-Tailed Classificationcited by 0