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 61–70 of 140 papers

TitleStatusHype
Rethinking the Localization in Weakly Supervised Object Localization—0
Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization—0
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
Constrained Sampling for Class-Agnostic Weakly Supervised Object Localization—0
Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization—0
Location-free Human Pose Estimation—0
Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition—0
Show:102550
← PrevPage 7 of 14Next →

No leaderboard results yet.