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 1–10 of 142 papers

TitleStatusHype
WeakSAM: Segment Anything Meets Weakly-supervised Instance-level RecognitionCode2
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized CutCode2
Weakly Supervised Object Detection in Chest X-Rays with Differentiable ROI Proposal Networks and Soft ROI PoolingCode1
LEOD: Label-Efficient Object Detection for Event CamerasCode1
Text-image Alignment for Diffusion-based PerceptionCode1
PDL: Regularizing Multiple Instance Learning with Progressive Dropout LayersCode1
Cyclic-Bootstrap Labeling for Weakly Supervised Object DetectionCode1
Domain-Adaptive Self-Supervised Pre-Training for Face & Body Detection in DrawingsCode1
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationCode1
ImaginaryNet: Learning Object Detectors without Real Images and AnnotationsCode1
Show:102550
← PrevPage 1 of 15Next →

No leaderboard results yet.