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 31–40 of 142 papers

TitleStatusHype
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationCode1
ImaginaryNet: Learning Object Detectors without Real Images and AnnotationsCode1
Object Discovery via Contrastive Learning for Weakly Supervised Object DetectionCode1
Active Learning Strategies for Weakly-supervised Object DetectionCode1
W2N:Switching From Weak Supervision to Noisy Supervision for Object DetectionCode1
Scaling Novel Object Detection with Weakly Supervised Detection TransformersCode1
SESS: Saliency Enhancing with Scaling and SlidingCode0
Online progressive instance-balanced sampling for weakly supervised object detection—0
Compositional Mixture Representations for Vision and Text—0
Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information—0
Show:102550
← PrevPage 4 of 15Next →

No leaderboard results yet.