SOTAVerified

Weakly Supervised Object Detection

Weakly Supervised Object Detection (WSOD) is the task of training object detectors with only image tag supervisions.

( Image credit: Soft Proposal Networks for Weakly Supervised Object Localization )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 142 papers

TitleStatusHype
Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in DrawingsCode1
Domain-Adaptive Object Detection via Uncertainty-Aware Distribution AlignmentCode1
Multiple Instance Detection Network with Online Instance Classifier RefinementCode1
Multiple instance learning on deep features for weakly supervised object detection with extreme domain shiftsCode1
Active Learning Strategies for Weakly-supervised Object DetectionCode1
Distilling Knowledge from Refinement in Multiple Instance Detection NetworksCode1
Boosting Weakly Supervised Object Detection with Progressive Knowledge TransferCode1
Cross-Domain Weakly-Supervised Object Detection through Progressive Domain AdaptationCode1
Comprehensive Attention Self-Distillation for Weakly-Supervised Object DetectionCode1
ImaginaryNet: Learning Object Detectors without Real Images and AnnotationsCode1
Show:102550
← PrevPage 2 of 15Next →

No leaderboard results yet.