On Label Granularity and Object Localization

Elijah Henry John Cole
Kimberly Wilber
Grant Van Horn
Xuan Yang
Pietro Perona
Serge Belongie
Andrew Howard
Mac Aodha, Oisin
European Conference on Computer Vision, Springer (2022), pp. 604-620

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.

Research Areas