mlsanityData to 7 Oct 2026

Parametric Information Maximization for Generalized Category Discovery

arXiv 2212.00334 ↗First posted 1 Dec 2022cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

We introduce a Parametric Information Maximization (PIM) model for the Generalized Category Discovery (GCD) problem. Specifically, we propose a bi-level optimization formulation, which explores a parameterized family of objective functions, each evaluating a weighted mutual information between the features and the latent labels, subject to supervision constraints from the labeled samples. Our formulation mitigates the class-balance bias encoded in standard information maximization approaches, thereby handling effectively both short-tailed and long-tailed data sets. We report extensive experiments and comparisons demonstrating that our PIM model consistently sets new state-of-the-art performances in GCD across six different datasets, more so when dealing with challenging fine-grained problems.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 39 of its 55 references that are in the map. First posted on arXiv 1 Dec 2022.

Builds on

39 of 55 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 2020Supervised Contrastive Learningcited by 2,803
  6. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  7. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  8. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  9. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  10. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  11. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  12. 2015Towards Open Set Deep Networkscited by 533
27 more
  1. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  2. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  3. 2019On Mutual Information Maximization for Representation Learningcited by 315
  4. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  5. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 223
  6. 2022Generalized Category Discoverycited by 209
  7. 2021Open-World Semi-Supervised Learningcited by 165
  8. 2021A Unified Objective for Novel Class Discoverycited by 161
  9. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  10. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 141
  11. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  12. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 119
  13. 2022SimMatch: Semi-supervised Learning with Similarity Matchingcited by 118
  14. 2021AutoNovel: Automatically Discovering and Learning Novel Visual Categoriescited by 116
  15. 2021Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillationcited by 104
  16. 2020A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossescited by 100
  17. 2020OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open Worldcited by 93
  18. 2019The Herbarium Challenge 2019 Datasetcited by 59
  19. 2021Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Datacited by 55
  20. 2021Source-Free Domain Adaptation for Image Segmentationcited by 45
  21. 2018Deep clustering: On the link between discriminative models and K-meanscited by 37
  22. 2020Exploring Category-Agnostic Clusters for Open-Set Domain Adaptationcited by 27
  23. 2022Realistic Evaluation of Transductive Few-Shot Learningcited by 26
  24. 2019Entropic Out-of-Distribution Detectioncited by 21
  25. 2013An Information-Theoretic Analysis of Hard and Soft Assignment Methods for Clusteringcited by 17
  26. 2015Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutionscited by 7
  27. 2022Mutual Information-guided Knowledge Transfer for Novel Class Discoverycited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 7; 2025: 17; 2026: 12.

39 papers.

Sort:

By area:

  1. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  2. 2024Contrastive Mean-Shift Learning for Generalized Category Discoverycited by 39
  3. 2024SelEx: Self-Expertise in Fine-Grained Generalized Category Discoverycited by 34
  4. 2024Active Generalized Category Discoverycited by 31
  5. 2023Incremental Generalized Category Discoverycited by 25
  6. 2025Hyperbolic Category Discoverycited by 20
  7. 2024Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discoverycited by 19
  8. 2024Happy: A Debiased Learning Framework for Continual Generalized Category Discoverycited by 18
  9. 2025Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancementcited by 13
  10. 2025Dissecting Generalized Category Discovery: Multiplex Consensus under Self-Deconstructioncited by 13
  11. 2024CDAD-Net: Bridging Domain Gaps in Generalized Category Discoverycited by 12
  12. 2025MOS: Modeling Object-Scene Associations in Generalized Category Discoverycited by 10
27 more
  1. 2025Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discoverycited by 9
  2. 2023Human-in-the-Loop Visual Re-ID for Population Size Estimationcited by 7
  3. 2025SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discoverycited by 7
  4. 2025Joint Out-of-Distribution Filtering and Data Discovery Active Learningcited by 6
  5. 2025When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approachcited by 5
  6. 2025Consistent Supervised-Unsupervised Alignment for Generalized Category Discoverycited by 5
  7. 2025Category Discovery: An Open-World Perspectivecited by 5
  8. 2025Generalized Category Discovery via Token Manifold Capacity Learningcited by 3
  9. 2025A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attentioncited by 3
  10. 2024A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorizationcited by 2
  11. 2025Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Expertscited by 2
  12. 2025HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discoverycited by 2
  13. 2025Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learningcited by 1
  14. 2026GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discoverycited by 1
  15. 2025Component Adaptive Clustering for Generalized Category Discoverycited by 0
  16. 2025Language-Aware Information Maximization for Transductive Few-Shot CLIPcited by 0
  17. 2026Information Maximization for Long-Tailed Semi-Supervised Domain Generalizationcited by 0
  18. 2026FOCUS: Bridging Fine-Grained Recognition and Open-World Discovery across Domainscited by 0
  19. 2026Learning Like Humans: Analogical Concept Learning for Generalized Category Discoverycited by 0
  20. 2026The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discoverycited by 0
  21. 2026OmniGCD: Abstracting Generalized Category Discovery for Modality Agnosticismcited by 0
  22. 2026Identifying Latent Concepts and Structures for Generalized Category Discoverycited by 0
  23. 2026Virtual Category-Guided Continual Generalized Category Discoverycited by 0
  24. 2026Fourier Self-Supervision for Fine-Grained Generalized Category Discoverycited by 0
  25. 2026CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalizationcited by 0
  26. 2026Test-Time Generalized Category Discoverycited by 0
  27. 2026Generalized Biomedicine Discoverycited by 0