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 1–10 of 140 papers

TitleStatusHype
Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic SegmentationCode2
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized CutCode2
C2AM: Contrastive Learning of Class-Agnostic Activation Map for Weakly Supervised Object Localization and Semantic SegmentationCode2
CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization PerspectiveCode1
Exploring Foveation and Saccade for Improved Weakly-Supervised LocalizationCode1
Background Activation Suppression for Weakly Supervised Object Localization and Semantic SegmentationCode1
FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object LocalizationCode1
Generative Prompt Model for Weakly Supervised Object LocalizationCode1
Open-World Weakly-Supervised Object LocalizationCode1
Spatial-Aware Token for Weakly Supervised Object LocalizationCode1
Show:102550
← PrevPage 1 of 14Next →

No leaderboard results yet.