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 121–130 of 140 papers

TitleStatusHype
Modularized Textual Grounding for Counterfactual ResilienceCode0
TeD-Loc: Text Distillation for Weakly Supervised Object LocalizationCode0
Combinational Class Activation Maps for Weakly Supervised Object LocalizationCode0
Attention-based Dropout Layer for Weakly Supervised Object LocalizationCode0
In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object LocalizationCode0
Background-aware Classification Activation Map for Weakly Supervised Object LocalizationCode0
Pairwise Similarity Knowledge Transfer for Weakly Supervised Object LocalizationCode0
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action LocalizationCode0
Attributional Robustness Training using Input-Gradient Spatial AlignmentCode0
Knowledge-guided Causal Intervention for Weakly-supervised Object LocalizationCode0
Show:102550
← PrevPage 13 of 14Next →

No leaderboard results yet.