mlsanityData to 7 Oct 2026

DoubleMatch: Improving Semi-Supervised Learning with Self-Supervision

arXiv 2205.05575 ↗First posted 11 May 2022cs.LG cs.CV stat.MLcited by 8

Not on the map. Why?

Abstract (arXiv)

Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increasingly popular. SSL is a family of methods, which in addition to a labeled training set, also use a sizable collection of unlabeled data for fitting a model. Most of the recent successful SSL methods are based on pseudo-labeling approaches: letting confident model predictions act as training labels. While these methods have shown impressive results on many benchmark datasets, a drawback of this approach is that not all unlabeled data are used during training. We propose a new SSL algorithm, DoubleMatch, which combines the pseudo-labeling technique with a self-supervised loss, enabling the model to utilize all unlabeled data in the training process. We show that this method achieves state-of-the-art accuracies on multiple benchmark datasets while also reducing training times compared to existing SSL methods. Code is available at https://github.com/walline/doublematch.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 11 May 2022.

Builds on

31 of 44 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  9. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  10. 2016Wide Residual Networkscited by 3,057
  11. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  12. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
19 more
  1. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  2. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  3. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  4. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  5. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  6. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  7. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  8. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  9. 2020Meta Pseudo Labelscited by 372
  10. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  11. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  12. 2019Interpolation Consistency Training for Semi-Supervised Learningcited by 248
  13. 2015Semi-Supervised Learning with Ladder Networkscited by 246
  14. 2021Dash: Semi-Supervised Learning with Dynamic Thresholdingcited by 147
  15. 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
  16. 2021All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-trainingcited by 32
  17. 2019Fine-Grained Segmentation Networks: Self-Supervised Segmentation for Improved Long-Term Visual Localizationcited by 24
  18. 2021DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samplescited by 18
  19. 2020Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learningcited by 14

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 4.

8 papers.

  1. 2023Boosting Semi-Supervised Learning by Exploiting All Unlabeled Datacited by 26
  2. 2023ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learningcited by 13
  3. 2023Improving Open-Set Semi-Supervised Learning with Self-Supervisioncited by 6
  4. 2024Exploring Semi-Supervised Learning for Online Mappingcited by 6
  5. 2024ProSub: Probabilistic Open-Set Semi-Supervised Learning with Subspace-Based Out-of-Distribution Detectioncited by 3
  6. 2023Feature Space Renormalization for Semi-supervised Learningcited by 0
  7. 2024Semi-supervised 2D Human Pose Estimation via Adaptive Keypoint Maskingcited by 0
  8. 2024CoVLM: Leveraging Consensus from Vision-Language Models for Semi-supervised Multi-modal Fake News Detectioncited by 0