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 81–90 of 142 papers

TitleStatusHype
Two-phase weakly supervised object detection with pseudo ground truth mining—0
Universal Bounding Box Regression and Its Applications—0
Utilizing the Instability in Weakly Supervised Object Detection—0
W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection—0
Weakly Supervised Cascaded Convolutional Networks—0
Weakly Supervised Instance Segmentation by Deep Community Learning—0
Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization—0
Weakly Supervised Localization using Deep Feature Maps—0
Weakly supervised object detection using pseudo-strong labels—0
Weakly Supervised Object Detection with Pointwise Mutual Information—0
Show:102550
← PrevPage 9 of 15Next →

No leaderboard results yet.