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
Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization—0
Open-World Weakly-Supervised Object LocalizationCode1
Spatial-Aware Token for Weakly Supervised Object LocalizationCode1
Knowledge-guided Causal Intervention for Weakly-supervised Object LocalizationCode0
Category-aware Allocation Transformer for Weakly Supervised Object Localization—0
Adversarial Normalization: I Can Visualize Everything (ICE)Code0
Expeditious Saliency-guided Mix-up through Random Gradient ThresholdingCode0
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationCode1
Dual Progressive Transformations for Weakly Supervised Semantic SegmentationCode1
Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization—0
Show:102550
← PrevPage 3 of 14Next →

No leaderboard results yet.