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 41–50 of 142 papers

TitleStatusHype
Spatial Likelihood Voting with Self-Knowledge Distillation for Weakly Supervised Object Detection—0
Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth BoxesCode1
SIOD: Single Instance Annotated Per Category Per Image for Object DetectionCode1
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized CutCode2
H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object DetectionCode1
Weakly Supervised Rotation-Invariant Aerial Object Detection NetworkCode1
Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection—0
Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection—0
Learning Better Visual Representations for Weakly-Supervised Object Detection Using Natural Language Supervision—0
PGTRNet: Two-phase Weakly Supervised Object Detection with Pseudo Ground Truth Refinement—0
Show:102550
← PrevPage 5 of 15Next →

No leaderboard results yet.