mlsanityData to 7 Oct 2026

Contrastive Learning for Online Semi-Supervised General Continual Learning

arXiv 2207.05615 ↗First posted 12 Jul 2022cs.LG cs.AI cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We study Online Continual Learning with missing labels and propose SemiCon, a new contrastive loss designed for partly labeled data. We demonstrate its efficiency by devising a memory-based method trained on an unlabeled data stream, where every data added to memory is labeled using an oracle. Our approach outperforms existing semi-supervised methods when few labels are available, and obtain similar results to state-of-the-art supervised methods while using only 2.6% of labels on Split-CIFAR10 and 10% of labels on Split-CIFAR100.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 12 Jul 2022.

Builds on

20 of 27 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  5. 2020Supervised Contrastive Learningcited by 2,803
  6. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  8. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  9. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  10. 2018Experience Replay for Continual Learningcited by 1,074
  11. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  12. 2021Online Continual Learning in Image Classification: An Empirical Surveycited by 242
8 more
  1. 2018Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselinescited by 228
  2. 2019Continual Unsupervised Representation Learningcited by 147
  3. 2021Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learningcited by 140
  4. 2021Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffercited by 30
  5. 2019Unsupervised Progressive Learning and the STAM Architecturecited by 29
  6. 2021Continual Semi-Supervised Learning through Contrastive Interpolation Consistencycited by 25
  7. 2021Unsupervised Continual Learning Via Pseudo Labelscited by 18
  8. 2021Hypernetworks for Continual Semi-Supervised Learningcited by 11

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 0; 2025: 1.

4 papers.

  1. 2023Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learningcited by 5
  2. 2023Domain-Aware Augmentations for Unsupervised Online General Continual Learningcited by 1
  3. 2023New metrics for analyzing continual learnerscited by 0
  4. 2025From Offline to Online Memory-Free and Task-Free Continual Learning via Fine-Grained Hypergradientscited by 0