mlsanityData to 14 Oct 2026

OpenCon: Open-world Contrastive Learning

arXiv 2208.02764 ↗First posted 4 Aug 2022cs.LG cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Machine learning models deployed in the wild naturally encounter unlabeled samples from both known and novel classes. Challenges arise in learning from both the labeled and unlabeled data, in an open-world semi-supervised manner. In this paper, we introduce a new learning framework, open-world contrastive learning (OpenCon). OpenCon tackles the challenges of learning compact representations for both known and novel classes and facilitates novelty discovery along the way. We demonstrate the effectiveness of OpenCon on challenging benchmark datasets and establish competitive performance. On the ImageNet dataset, OpenCon significantly outperforms the current best method by 11.9% and 7.4% on novel and overall classification accuracy, respectively. Theoretically, OpenCon can be rigorously interpreted from an EM algorithm perspective--minimizing our contrastive loss partially maximizes the likelihood by clustering similar samples in the embedding space. The code is available at https://github.com/deeplearning-wisc/opencon.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Builds on 71 of its 93 references that are in the map. First posted on arXiv 4 Aug 2022.

Builds on

71 of 93 references.

References · 71

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  9. 2020Supervised Contrastive Learningcited by 2,829
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  11. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
38 more
  1. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  2. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  3. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  4. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  5. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  6. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  7. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  8. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 560
  9. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  10. 2015Towards Open Set Deep Networkscited by 538
  11. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  12. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  13. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  14. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  15. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  16. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  17. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 326
  18. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  19. 2021Co2L: Contrastive Continual Learningcited by 244
  20. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  21. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 225
  22. 2021Parametric Contrastive Learningcited by 217
  23. 2022Generalized Category Discoverycited by 211
  24. 2021Self-supervised Pretraining of Visual Features in the Wildcited by 198
  25. 2020CoMatch: Semi-supervised Learning with Contrastive Graph Regularizationcited by 167
  26. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  27. 2021Open-World Semi-Supervised Learningcited by 165
  28. 2021A Unified Objective for Novel Class Discoverycited by 162
  29. 2021Targeted Supervised Contrastive Learning for Long-Tailed Recognitioncited by 132
  30. 2017Learning to cluster in order to transfer across domains and taskscited by 128
  31. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 121
  32. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  33. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
  34. 2020Conditional Gaussian Distribution Learning for Open Set Recognitioncited by 104
  35. 2021Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillationcited by 104
  36. 2019Multi-class Classification without Multi-class Labelscited by 100
  37. 2021Can multi-label classification networks know what they don't know?cited by 100
  38. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 15; 2024: 10; 2025: 5; 2026: 2.

33 papers.

Sort:

By area:

  1. 2022Parametric Classification for Generalized Category Discovery: A Baseline Studycited by 113
  2. 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
  3. 2023No Representation Rules Them All in Category Discoverycited by 61
  4. 2023Federated Generalized Category Discoverycited by 27
  5. 2023A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learningcited by 22
  6. 2023When and How Does Known Class Help Discover Unknown Ones? Provable Understanding Through Spectral Analysiscited by 21
  7. 2025Hyperbolic Category Discoverycited by 20
  8. 2025DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discoverycited by 15
  9. 2023Towards Distribution-Agnostic Generalized Category Discoverycited by 12
  10. 2024Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discoverycited by 9
  11. 2025SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discoverycited by 7
  12. 2024Deep Active Learning in the Open Worldcited by 5
21 more
  1. 2025Category Discovery: An Open-World Perspectivecited by 5
  2. 2023Federated Continual Novel Class Learningcited by 4
  3. 2023Generalized Categories Discovery for Long-tailed Recognitioncited by 4
  4. 2023ImbaGCD: Imbalanced Generalized Category Discoverycited by 3
  5. 2024Bridging OOD Detection and Generalization: A Graph-Theoretic Viewcited by 3
  6. 2024OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learningcited by 3
  7. 2023Discovering COVID-19 Coughing and Breathing Patterns from Unlabeled Data Using Contrastive Learning with Varying Pre-Training Domainscited by 2
  8. 2023A Practical Approach to Novel Class Discovery in Tabular Datacited by 2
  9. 2024A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorizationcited by 2
  10. 2023Semi-Supervised Learning in the Few-Shot Zero-Shot Scenariocited by 1
  11. 2023Detecting and Learning Out-of-Distribution Data in the Open world: Algorithm and Theorycited by 1
  12. 2023Evaluation of human-model prediction difference on the Internet Scale of Datacited by 1
  13. 2024Open-World Semi-Supervised Learning for Node Classificationcited by 1
  14. 2024Composing Novel Classes: A Concept-Driven Approach to Generalized Category Discoverycited by 1
  15. 2026Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discoverycited by 1
  16. 2023Adapting Self-Supervised Representations to Multi-Domain Setupscited by 0
  17. 2024Towards Realistic Long-tailed Semi-supervised Learning in an Open Worldcited by 0
  18. 2024Rethinking Open-World Semi-Supervised Learning: Distribution Mismatch and Inductive Inferencecited by 0
  19. 2024POWN: Prototypical Open-World Node Classificationcited by 0
  20. 2025Long-Tailed Learning for Generalized Category Discoverycited by 0
  21. 2026The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discoverycited by 0