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
Cyclic-Bootstrap Labeling for Weakly Supervised Object DetectionCode1
Read, look and detect: Bounding box annotation from image-caption pairs—0
Extracting Complex Named Entities in Legal Documents via Weakly Supervised Object Detection—0
Towards Precise Weakly Supervised Object Detection via Interactive Contrastive Learning of Context Information—0
DETR with Additional Global Aggregation for Cross-domain Weakly Supervised Object Detection—0
Transformer-based Multi-Instance Learning for Weakly Supervised Object Detection—0
Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depth—0
VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object DetectionCode0
D2DF2WOD: Learning Object Proposals for Weakly-Supervised Object Detection via Progressive Domain Adaptation—0
Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in DrawingsCode1
Show:102550
← PrevPage 3 of 15Next →

No leaderboard results yet.