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 51–60 of 140 papers

TitleStatusHype
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action LocalizationCode0
Attributional Robustness Training using Input-Gradient Spatial AlignmentCode0
Progressive Representation Adaptation for Weakly Supervised Object LocalizationCode0
GridMix: Strong regularization through local context mappingCode0
DANet: Divergent Activation for Weakly Supervised Object LocalizationCode0
Knowledge-guided Causal Intervention for Weakly-supervised Object LocalizationCode0
Min-Entropy Latent Model for Weakly Supervised Object DetectionCode0
Convolutional STN for Weakly Supervised Object LocalizationCode0
Modularized Textual Grounding for Counterfactual ResilienceCode0
A Realistic Protocol for Evaluation of Weakly Supervised Object LocalizationCode0
Show:102550
← PrevPage 6 of 14Next →

No leaderboard results yet.