mlsanityData to 7 Oct 2026

UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning

arXiv 2103.10773 ↗First posted 19 Mar 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Momentum Contrast (MoCo) achieves great success for unsupervised visual representation. However, there are a lot of supervised and semi-supervised datasets, which are already labeled. To fully utilize the label annotations, we propose Unified Momentum Contrast (UniMoCo), which extends MoCo to support arbitrary ratios of labeled data and unlabeled data training. Compared with MoCo, UniMoCo has two modifications as follows: (1) Different from a single positive pair in MoCo, we maintain multiple positive pairs on-the-fly by comparing the query label to a label queue. (2) We propose a Unified Contrastive(UniCon) loss to support an arbitrary number of positives and negatives in a unified pair-wise optimization perspective. Our UniCon is more reasonable and powerful than the supervised contrastive loss in theory and practice. In our experiments, we pre-train multiple UniMoCo models with different ratios of ImageNet labels and evaluate the performance on various downstream tasks. Experiment results show that UniMoCo generalizes well for unsupervised, semi-supervised and supervised visual representation learning.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 44 of its 60 references that are in the map. First posted on arXiv 19 Mar 2021.

Builds on

44 of 60 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  8. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  9. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  10. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  11. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  12. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
32 more
  1. 2015Fast R-CNNcited by 2,930
  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. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  6. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  7. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  8. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  9. 2019Contrastive Multiview Codingcited by 1,297
  10. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  11. 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,041
  12. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  13. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  14. 2019When Does Label Smoothing Help?cited by 985
  15. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  16. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  17. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  18. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  19. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
  20. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  21. 2013Network In Networkcited by 600
  22. 2018Do Better ImageNet Models Transfer Better?cited by 560
  23. 2017Large Batch Training of Convolutional Networkscited by 529
  24. 2019Self-labelling via simultaneous clustering and representation learningcited by 525
  25. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
  26. 2018Rethinking ImageNet Pre-trainingcited by 376
  27. 2020A Metric Learning Reality Checkcited by 317
  28. 2019Unsupervised Embedding Learning via Invariant and Spreading Instance Featurecited by 231
  29. 2019Local Aggregation for Unsupervised Learning of Visual Embeddingscited by 204
  30. 2017Interpreting Deep Visual Representations via Network Dissectioncited by 103
  31. 2014Training Convolutional Networks with Noisy Labelscited by 47
  32. 2019Cross-Entropy Loss and Low-Rank Features Have Responsibility for Adversarial Examplescited by 17

Built on by

Cited by year

Citing papers per year: 2022: 4.

4 papers.

  1. 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
  2. 2022SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understandingcited by 28
  3. 2022ProCo: Prototype-aware Contrastive Learning for Long-tailed Medical Image Classificationcited by 25
  4. 2022Evaluation of Contrastive Learning with Various Code Representations for Code Clone Detectioncited by 3