Skip to yearly menu bar Skip to main content


Poster

Fine-grained Classes and How to Find Them

Matej Grcic · Artyom Gadetsky · Maria Brbic

Hall C 4-9 #412
[ ] [ Project Page ]
Wed 24 Jul 2:30 a.m. PDT — 4 a.m. PDT

Abstract:

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.

Live content is unavailable. Log in and register to view live content