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

Showing 110 of 142 papers

TitleStatusHype
Class Agnostic Instance-level Descriptor for Visual Instance Search0
Self-Classification Enhancement and Correction for Weakly Supervised Object Detection0
Enhancing Weakly-Supervised Object Detection on Static Images through (Hallucinated) Motion0
Weakly Supervised Object Detection for Automatic Tooth-marked Tongue RecognitionCode0
Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical videoCode0
HUWSOD: Holistic Self-training for Unified Weakly Supervised Object DetectionCode0
Smart Feature is What You NeedCode0
Negative Prototypes Guided Contrastive Learning for WSOD0
Sparse Generation: Making Pseudo Labels Sparse for Point Weakly Supervised Object Detection on Low Data VolumeCode0
WeakSAM: Segment Anything Meets Weakly-supervised Instance-level RecognitionCode2
Show:102550
← PrevPage 1 of 15Next →

No leaderboard results yet.