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 11–20 of 140 papers

TitleStatusHype
Towards Two-Stream Foveation-based Active Vision Learning—0
CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization PerspectiveCode1
Exploring Foveation and Saccade for Improved Weakly-Supervised LocalizationCode1
Multiscale Vision Transformer With Deep Clustering-Guided Refinement for Weakly Supervised Object Localization—0
DiPS: Discriminative Pseudo-Label Sampling with Self-Supervised Transformers for Weakly Supervised Object LocalizationCode0
Background Activation Suppression for Weakly Supervised Object Localization and Semantic SegmentationCode1
FDCNet: Feature Drift Compensation Network for Class-Incremental Weakly Supervised Object LocalizationCode1
Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization—0
Rethinking the Localization in Weakly Supervised Object Localization—0
Generative Prompt Model for Weakly Supervised Object LocalizationCode1
Show:102550
← PrevPage 2 of 14Next →

No leaderboard results yet.