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 91–100 of 140 papers

TitleStatusHype
Density-Based Region Search with Arbitrary Shape for Object Localization—0
Discriminative Sampling of Proposals in Self-Supervised Transformers for Weakly Supervised Object Localization—0
Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition—0
Dual-attention Focused Module for Weakly Supervised Object Localization—0
Entropy Guided Adversarial Model for Weakly Supervised Object Localization—0
Erasing Integrated Learning: A Simple Yet Effective Approach for Weakly Supervised Object Localization—0
Weakly-supervised Object Localization for Few-shot Learning and Fine-grained Few-shot Learning—0
Fine-Grained Attention for Weakly Supervised Object Localization—0
Foreground Activation Maps for Weakly Supervised Object Localization—0
GridMix: Strong regularization through local context mapping—0
Show:102550
← PrevPage 10 of 14Next →

No leaderboard results yet.