Fine-grained Classes and How to Find Them
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911920061153280 |
|---|---|
| author | Grcić, Matej Gadetsky, Artyom Brbić, Maria |
| author_facet | Grcić, Matej Gadetsky, Artyom Brbić, Maria |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_11070 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fine-grained Classes and How to Find Them Grcić, Matej Gadetsky, Artyom Brbić, Maria Machine Learning Computer Vision and Pattern Recognition 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. |
| title | Fine-grained Classes and How to Find Them |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.11070 |