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 21–30 of 140 papers

TitleStatusHype
A Generic Visualization Approach for Convolutional Neural NetworksCode1
Geometry Constrained Weakly Supervised Object LocalizationCode1
Dual-attention Guided Dropblock Module for Weakly Supervised Object LocalizationCode1
Bagging Regional Classification Activation Maps for Weakly Supervised Object LocalizationCode1
CREAM: Weakly Supervised Object Localization via Class RE-Activation MappingCode1
An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localizationCode1
FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object LocalizationCode1
Eigen-CAM: Class Activation Map using Principal ComponentsCode1
LayerCAM: Exploring Hierarchical Class Activation Maps for LocalizationCode1
Improving Weakly-supervised Object Localization via Causal InterventionCode1
Show:102550
← PrevPage 3 of 14Next →

No leaderboard results yet.