mlsanityData to 7 Oct 2026

Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery

arXiv 2603.19918 ↗First posted 20 Mar 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Generalized Category Discovery (GCD) seeks to uncover novel categories in unlabeled data while preserving recognition of known categories, yet prevailing visual-only pipelines and the loose coupling between supervised learning and discovery often yield brittle boundaries on fine-grained, look-alike categories. We introduce the Analogical Textual Concept Generator (ATCG), a plug-and-play module that analogizes from labeled knowledge to new observations, forming textual concepts for unlabeled samples. Fusing these analogical textual concepts with visual features turns discovery into a visual-textual reasoning process, transferring prior knowledge to novel data and sharpening category separation. ATCG attaches to both parametric and clustering style GCD pipelines and requires no changes to their overall design. Across six benchmarks, ATCG consistently improves overall, known-class, and novel-class performance, with the largest gains on fine-grained data. Our code is available at: https://github.com/zhou-9527/AnaLogical-GCD.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 28 of its 42 references that are in the map. First posted on arXiv 20 Mar 2026.

Builds on

28 of 42 references.

References · 28

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  3. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  4. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  5. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  6. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,548
  7. 2021FILIP: Fine-grained Interactive Language-Image Pre-Trainingcited by 626
  8. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 355
  9. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  10. 2022Generalized Category Discoverycited by 209
  11. 2021Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learningcited by 187
  12. 2022Parametric Classification for Generalized Category Discovery: A Baseline Studycited by 113
16 more
  1. 2023Dynamic Conceptional Contrastive Learning for Generalized Category Discoverycited by 90
  2. 2022PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discoverycited by 85
  3. 2023Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discoverycited by 72
  4. 2019The Herbarium Challenge 2019 Datasetcited by 59
  5. 2022Parametric Information Maximization for Generalized Category Discoverycited by 39
  6. 2024Contrastive Mean-Shift Learning for Generalized Category Discoverycited by 39
  7. 2024SelEx: Self-Expertise in Fine-Grained Generalized Category Discoverycited by 34
  8. 2024Active Generalized Category Discoverycited by 31
  9. 2024GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discoverycited by 26
  10. 2025Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution Regularizationcited by 6
  11. 2025Consistent Supervised-Unsupervised Alignment for Generalized Category Discoverycited by 5
  12. 2024Zoom-shot: Fast and Efficient Unsupervised Zero-Shot Transfer of CLIP to Vision Encoders with Multimodal Losscited by 3
  13. 2025Learn by Reasoning: Analogical Weight Generation for Few-Shot Class-Incremental Learningcited by 3
  14. 2025Beyond CLIP Generalization: Against Forward&Backward Forgetting Adapter for Continual Learning of Vision-Language Modelscited by 2
  15. 2014Analogy-Based and Case-Based Reasoning: Two sides of the same coincited by 1
  16. 2026GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discoverycited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025GLEAN: Active Generalized Category Discovery with Diverse LLM Feedback
  2. 2024Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discovery
  3. 2026Test-Time Generalized Category Discovery
  4. 2026Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Models
  5. 2025HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery
  6. 2025Few-shot Novel Category Discovery
  7. 2024GraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class Discovery
  8. 2025Video-based Generalized Category Discovery via Memory-Guided Consistency-Aware Contrastive Learning