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 81–90 of 140 papers

TitleStatusHype
In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object LocalizationCode0
Entropy Guided Adversarial Model for Weakly Supervised Object Localization—0
Rethinking Class Activation Mapping for Weakly Supervised Object LocalizationCode1
Eigen-CAM: Class Activation Map using Principal ComponentsCode1
Geometry Constrained Weakly Supervised Object LocalizationCode1
A Generic Visualization Approach for Convolutional Neural NetworksCode1
Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and DatasetsCode1
Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement MapsCode0
Erasing Integrated Learning: A Simple Yet Effective Approach for Weakly Supervised Object Localization—0
Distilling Knowledge from Refinement in Multiple Instance Detection NetworksCode1
Show:102550
← PrevPage 9 of 14Next →

No leaderboard results yet.