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 31–40 of 140 papers

TitleStatusHype
Keep CALM and Improve Visual Feature AttributionCode1
Improving Weakly-supervised Object Localization via Causal InterventionCode1
TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object LocalizationCode1
Unveiling the Potential of Structure Preserving for Weakly Supervised Object LocalizationCode1
Rethinking Class Activation Mapping for Weakly Supervised Object LocalizationCode1
Eigen-CAM: Class Activation Map using Principal ComponentsCode1
A Generic Visualization Approach for Convolutional Neural NetworksCode1
Geometry Constrained Weakly Supervised Object LocalizationCode1
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and DatasetsCode1
Distilling Knowledge from Refinement in Multiple Instance Detection NetworksCode1
Show:102550
← PrevPage 4 of 14Next →

No leaderboard results yet.