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
Object Discovery via Contrastive Learning for Weakly Supervised Object DetectionCode1
W2N:Switching From Weak Supervision to Noisy Supervision for Object DetectionCode1
Active Learning Strategies for Weakly-supervised Object DetectionCode1
Scaling Novel Object Detection with Weakly Supervised Detection TransformersCode1
Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth BoxesCode1
SIOD: Single Instance Annotated Per Category Per Image for Object DetectionCode1
H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object DetectionCode1
Weakly Supervised Rotation-Invariant Aerial Object Detection NetworkCode1
Boosting Weakly Supervised Object Detection via Learning Bounding Box AdjustersCode1
UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object DetectionCode1
Show:102550
← PrevPage 2 of 15Next →

No leaderboard results yet.