mlsanityData to 14 Oct 2026

SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discovery

arXiv 2510.18740 ↗First posted 21 Oct 2025cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

This paper investigates the problem of Generalized Category Discovery (GCD). Given a partially labelled dataset, GCD aims to categorize all unlabelled images, regardless of whether they belong to known or unknown classes. Existing approaches typically depend on either single-level semantics or manually designed abstract hierarchies, which limit their generalizability and scalability. To address these limitations, we introduce a SEmantic-aware hierArchical Learning framework (SEAL), guided by naturally occurring and easily accessible hierarchical structures. Within SEAL, we propose a Hierarchical Semantic-Guided Soft Contrastive Learning approach that exploits hierarchical similarity to generate informative soft negatives, addressing the limitations of conventional contrastive losses that treat all negatives equally. Furthermore, a Cross-Granularity Consistency (CGC) module is designed to align the predictions from different levels of granularity. SEAL consistently achieves state-of-the-art performance on fine-grained benchmarks, including the SSB benchmark, Oxford-Pet, and the Herbarium19 dataset, and further demonstrates generalization on coarse-grained datasets. Project page: https://visual-ai.github.io/seal/

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 52 of its 74 references that are in the map. First posted on arXiv 21 Oct 2025.

Builds on

52 of 74 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  8. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  9. 2017Mask R-CNNcited by 7,277
  10. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  11. 2015Fast R-CNNcited by 2,933
  12. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
38 more
  1. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  2. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
  3. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  4. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 316
  5. 2019SOLO: Segmenting Objects by Locationscited by 289
  6. 2019Learning to Discover Novel Visual Categories via Deep Transfer Clusteringcited by 225
  7. 2022Generalized Category Discoverycited by 211
  8. 2021Open-World Semi-Supervised Learningcited by 165
  9. 2021A Unified Objective for Novel Class Discoverycited by 162
  10. 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 143
  11. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  12. 2021Neighborhood Contrastive Learning for Novel Class Discoverycited by 121
  13. 2021AutoNovel: Automatically Discovering and Learning Novel Visual Categoriescited by 116
  14. 2022Parametric Classification for Generalized Category Discovery: A Baseline Studycited by 113
  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. 2023Dynamic Conceptional Contrastive Learning for Generalized Category Discoverycited by 92
  18. 2022PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discoverycited by 87
  19. 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
  20. 2023No Representation Rules Them All in Category Discoverycited by 61
  21. 2019The Herbarium Challenge 2019 Datasetcited by 60
  22. 2022Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Frameworkcited by 59
  23. 2021Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Datacited by 55
  24. 2024SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuningcited by 51
  25. 2022XCon: Learning with Experts for Fine-grained Category Discoverycited by 50
  26. 2022Novel Class Discovery without Forgettingcited by 39
  27. 2022Parametric Information Maximization for Generalized Category Discoverycited by 39
  28. 2023Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discoverycited by 39
  29. 2024SelEx: Self-Expertise in Fine-Grained Generalized Category Discoverycited by 34
  30. 2022OpenCon: Open-world Contrastive Learningcited by 33
  31. 2023CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discoverycited by 26
  32. 2025Solving the Catastrophic Forgetting Problem in Generalized Category Discoverycited by 26
  33. 2024HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shiftscited by 23
  34. 2025Hyperbolic Category Discoverycited by 20
  35. 2023TransNuSeg: A Lightweight Multi-Task Transformer for Nuclei Segmentationcited by 15
  36. 2025DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discoverycited by 15
  37. 2023ProTeCt: Prompt Tuning for Taxonomic Open Set Classificationcited by 12
  38. 2017Joint Hierarchical Category Structure Learning and Large-Scale Image Classificationcited by 6

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026MATANet: A Multi-context Attention and Taxonomy-Aware Network for Fine-Grained Underwater Recognition of Marine Speciescited by 1
  2. 2026Comparing Euclidean and Hyperbolic K-Means for Generalized Category Discoverycited by 0
  3. 2026The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discoverycited by 0
  4. 2026Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Modelscited by 0
  5. 2026Fourier Self-Supervision for Fine-Grained Generalized Category Discoverycited by 0
  6. 2026CloSeR: Unified Relational Distillation from Closed-Set Teachers for Category Discoverycited by 0
  7. 2026Generalized Biomedicine Discoverycited by 0