# Fine-grained Classes and How to Find Them

arXiv: https://arxiv.org/abs/2406.11070 · HTML: https://mlsanity.com/paper/2406.11070/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 16 Jun 2024.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [SCAN: Learning to Classify Images without Labels](https://mlsanity.com/paper/2005.12320/) (2020)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems](https://mlsanity.com/paper/2011.12945/) (2020)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [BREEDS: Benchmarks for Subpopulation Shift](https://mlsanity.com/paper/2008.04859/) (2020)
- [SPICE: Semantic Pseudo-labeling for Image Clustering](https://mlsanity.com/paper/2103.09382/) (2021)
- [Improving Generalization via Scalable Neighborhood Component Analysis](https://mlsanity.com/paper/1808.04699/) (2018)
- [Grafit: Learning fine-grained image representations with coarse labels](https://mlsanity.com/paper/2011.12982/) (2020)
- [Fine-grained Angular Contrastive Learning with Coarse Labels](https://mlsanity.com/paper/2012.03515/) (2020)
- [Efficient Algorithms for Learning from Coarse Labels](https://mlsanity.com/paper/2108.09805/) (2021)
- [MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset](https://mlsanity.com/paper/2303.12756/) (2023)
- [Strength from Weakness: Fast Learning Using Weak Supervision](https://mlsanity.com/paper/2002.08483/) (2020)
- [Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph](https://mlsanity.com/paper/1905.04042/) (2019)
- [Weakly Supervised Representation Learning with Coarse Labels](https://mlsanity.com/paper/2005.09681/) (2020)
- [The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning](https://mlsanity.com/paper/2311.02940/) (2023)
- [Weakly supervised training of universal visual concepts for multi-domain semantic segmentation](https://mlsanity.com/paper/2212.10340/) (2022)

## Built on by (most cited first, 2 of 2)

- [Large (Vision) Language Models are Unsupervised In-Context Learners](https://mlsanity.com/paper/2504.02349/) (2025)
- [Free-Grained Hierarchical Visual Recognition](https://mlsanity.com/paper/2510.14737/) (2025)

## 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.