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 21–30 of 142 papers

TitleStatusHype
Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in DrawingsCode1
Cross-Domain Weakly-Supervised Object Detection through Progressive Domain AdaptationCode1
Cyclic-Bootstrap Labeling for Weakly Supervised Object DetectionCode1
Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object DetectionCode1
Object Discovery via Contrastive Learning for Weakly Supervised Object DetectionCode1
Scaling Novel Object Detection with Weakly Supervised Detection TransformersCode1
SIOD: Single Instance Annotated Per Category Per Image for Object DetectionCode1
LEOD: Label-Efficient Object Detection for Event CamerasCode1
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationCode1
PDL: Regularizing Multiple Instance Learning with Progressive Dropout LayersCode1
Show:102550
← PrevPage 3 of 15Next →

No leaderboard results yet.