mlsanityData to 7 Oct 2026

MoBYv2AL: Self-supervised Active Learning for Image Classification

arXiv 2301.01531 ↗First posted 4 Jan 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Active learning(AL) has recently gained popularity for deep learning(DL) models. This is due to efficient and informative sampling, especially when the learner requires large-scale labelled datasets. Commonly, the sampling and training happen in stages while more batches are added. One main bottleneck in this strategy is the narrow representation learned by the model that affects the overall AL selection. We present MoBYv2AL, a novel self-supervised active learning framework for image classification. Our contribution lies in lifting MoBY, one of the most successful self-supervised learning algorithms, to the AL pipeline. Thus, we add the downstream task-aware objective function and optimize it jointly with contrastive loss. Further, we derive a data-distribution selection function from labelling the new examples. Finally, we test and study our pipeline robustness and performance for image classification tasks. We successfully achieved state-of-the-art results when compared to recent AL methods. Code available: https://github.com/razvancaramalau/MoBYv2AL

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 43 references that are in the map. First posted on arXiv 4 Jan 2023.

Builds on

33 of 43 references.

References · 33

  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. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  10. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  11. 2016Wide Residual Networkscited by 3,057
  12. 2020Exploring Simple Siamese Representation Learningcited by 2,853
21 more
  1. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  2. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  3. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  4. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  5. 2019Learning Loss for Active Learningcited by 335
  6. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 333
  7. 2019Variational Adversarial Active Learningcited by 284
  8. 2020CoMatch: Semi-supervised Learning with Contrastive Graph Regularizationcited by 167
  9. 2021Active Learning by Acquiring Contrastive Examplescited by 154
  10. 2020Contextual Diversity for Active Learningcited by 139
  11. 2021Self-Supervised Learning with Swin Transformerscited by 121
  12. 2019Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Costcited by 114
  13. 2013Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networkscited by 84
  14. 2020Task-Aware Variational Adversarial Active Learningcited by 84
  15. 2020Sequential Graph Convolutional Network for Active Learningcited by 69
  16. 2021Semi-Supervised Active Learning with Temporal Output Discrepancycited by 50
  17. 2021Reducing Label Effort: Self-Supervised meets Active Learningcited by 42
  18. 2017Cost-Effective Active Learning for Melanoma Segmentationcited by 40
  19. 2021Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outlierscited by 22
  20. 2020Active Learning for Bayesian 3D Hand Pose Estimationcited by 13
  21. 2020Confident Coreset for Active Learning in Medical Image Analysiscited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 2.

3 papers.

  1. 2023Benchmarking of Query Strategies: Towards Future Deep Active Learningcited by 1
  2. 2025Inconsistency-based Active Learning for LiDAR Object Detectioncited by 1
  3. 2025Active Learning Methods for Efficient Data Utilization and Model Performance Enhancementcited by 0