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 11–20 of 140 papers

TitleStatusHype
Bagging Regional Classification Activation Maps for Weakly Supervised Object LocalizationCode1
An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localizationCode1
TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object LocalizationCode1
Exploring Foveation and Saccade for Improved Weakly-Supervised LocalizationCode1
CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization PerspectiveCode1
Dual Progressive Transformations for Weakly Supervised Semantic SegmentationCode1
Background Activation Suppression for Weakly Supervised Object LocalizationCode1
Distilling Knowledge from Refinement in Multiple Instance Detection NetworksCode1
Background Activation Suppression for Weakly Supervised Object Localization and Semantic SegmentationCode1
Evaluating Weakly Supervised Object Localization Methods RightCode1
Show:102550
← PrevPage 2 of 14Next →

No leaderboard results yet.