Published July 20, 2022
| public
Discussion Paper
On Label Granularity and Object Localization
Chicago
An error occurred while generating the citation.
Abstract
Weakly supervised object localization (WSOL) aims to learn representations that encode object location using only image-level category labels. However, many objects can be labeled at different levels of granularity. Is it an animal, a bird, or a great horned owl? Which image-level labels should we use? In this paper we study the role of label granularity in WSOL. To facilitate this investigation we introduce iNatLoc500, a new large-scale fine-grained benchmark dataset for WSOL. Surprisingly, we find that choosing the right training label granularity provides a much larger performance boost than choosing the best WSOL algorithm. We also show that changing the label granularity can significantly improve data efficiency.
Additional Information
We thank the iNaturalist community for sharing images and species annotations. This work was supported by the Caltech Resnick Sustainability Institute, an NSF Graduate Research Fellowship (grant number DGE1745301), and the Pioneer Centre for AI (DNRF grant number P1).Additional details
- Eprint ID
- 118461
- Resolver ID
- CaltechAUTHORS:20221219-234038678
- Resnick Sustainability Institute
- NSF Graduate Research Fellowship
- DGE-1745301
- Danish National Research Foundation
- P1
- Created
-
2022-12-21Created from EPrint's datestamp field
- Updated
-
2023-06-02Created from EPrint's last_modified field
- Caltech groups
- Resnick Sustainability Institute