A Caltech Library Service

On Label Granularity and Object Localization

Cole, Elijah and Wilber, Kimberly and Van Horn, Grant and Yang, Xuan and Fornoni, Marco and Perona, Pietro and Belongie, Serge and Howard, Andrew and Mac Aodha, Oisin (2022) On Label Granularity and Object Localization. . (Unpublished)

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


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.

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Cole, Elijah0000-0001-6623-0966
Wilber, Kimberly0000-0001-7040-0251
Van Horn, Grant0000-0003-2953-9651
Fornoni, Marco0000-0001-5538-8012
Perona, Pietro0000-0002-7583-5809
Belongie, Serge0000-0002-0388-5217
Mac Aodha, Oisin0000-0002-5787-5073
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).
Group:Resnick Sustainability Institute
Funding AgencyGrant Number
Resnick Sustainability InstituteUNSPECIFIED
NSF Graduate Research FellowshipDGE-1745301
Danish National Research FoundationP1
Record Number:CaltechAUTHORS:20221219-234038678
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:118461
Deposited By: George Porter
Deposited On:21 Dec 2022 16:54
Last Modified:02 Jun 2023 01:28

Repository Staff Only: item control page