mlsanityData to 7 Oct 2026

Fine-grained Classes and How to Find Them

arXiv 2406.11070 ↗First posted 16 Jun 2024cs.LG cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

In many practical applications, coarse-grained labels are readily available compared to fine-grained labels that reflect subtle differences between classes. However, existing methods cannot leverage coarse labels to infer fine-grained labels in an unsupervised manner. To bridge this gap, we propose FALCON, a method that discovers fine-grained classes from coarsely labeled data without any supervision at the fine-grained level. FALCON simultaneously infers unknown fine-grained classes and underlying relationships between coarse and fine-grained classes. Moreover, FALCON is a modular method that can effectively learn from multiple datasets labeled with different strategies. We evaluate FALCON on eight image classification tasks and a single-cell classification task. FALCON outperforms baselines by a large margin, achieving 22% improvement over the best baseline on the tieredImageNet dataset with over 600 fine-grained classes.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 43 references that are in the map. First posted on arXiv 16 Jun 2024.

Builds on

24 of 43 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2023Segment Anythingcited by 8,158
  4. 2021Convex optimizationcited by 2,479
  5. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  6. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  7. 2019Self-labelling via simultaneous clustering and representation learningcited by 525
  8. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  9. 2020SCAN: Learning to Classify Images without Labelscited by 351
  10. 2022Generalized Category Discoverycited by 209
  11. 2020No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problemscited by 208
  12. 2021Open-World Semi-Supervised Learningcited by 165
12 more
  1. 2020BREEDS: Benchmarks for Subpopulation Shiftcited by 155
  2. 2021SPICE: Semantic Pseudo-labeling for Image Clusteringcited by 104
  3. 2018Improving Generalization via Scalable Neighborhood Component Analysiscited by 53
  4. 2020Grafit: Learning fine-grained image representations with coarse labelscited by 43
  5. 2020Fine-grained Angular Contrastive Learning with Coarse Labelscited by 30
  6. 2021Efficient Algorithms for Learning from Coarse Labelscited by 21
  7. 2023MaskCon: Masked Contrastive Learning for Coarse-Labelled Datasetcited by 21
  8. 2020Strength from Weakness: Fast Learning Using Weak Supervisioncited by 18
  9. 2019Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graphcited by 15
  10. 2020Weakly Supervised Representation Learning with Coarse Labelscited by 11
  11. 2023The Pursuit of Human Labeling: A New Perspective on Unsupervised Learningcited by 6
  12. 2022Weakly supervised training of universal visual concepts for multi-domain semantic segmentationcited by 5

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Large (Vision) Language Models are Unsupervised In-Context Learnerscited by 6
  2. 2025Free-Grained Hierarchical Visual Recognitioncited by 3