SOTAVerified

Weakly-Supervised Object Localization

Weakly supervised object localization (WSOL) learns to localize objects with only image-level labels, no object level labels (bonding boxes, etc.,) is needed. It is more attractive since image-level labels are much easier and cheaper to obtain.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 61–70 of 140 papers

TitleStatusHype
Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection—0
Shallow Feature Matters for Weakly Supervised Object LocalizationCode1
Normalization Matters in Weakly Supervised Object LocalizationCode1
LayerCAM: Exploring Hierarchical Class Activation Maps for LocalizationCode1
Strengthen Learning Tolerance for Weakly Supervised Object LocalizationCode0
Keep CALM and Improve Visual Feature AttributionCode1
Improving Few-shot Learning with Weakly-supervised Object Localization—0
MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization—0
Improving Weakly-supervised Object Localization via Causal InterventionCode1
Weakly Supervised Object Localization and Detection: A Survey—0
Show:102550
← PrevPage 7 of 14Next →

No leaderboard results yet.