SOTAVerified

Weakly-Supervised Object Localization

Weakly supervised object localization (WSOL) learns to localize objects with only image-level labels, no object level labels (bonding boxes, etc.,) is needed. It is more attractive since image-level labels are much easier and cheaper to obtain.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–110 of 140 papers

TitleStatusHype
Combinational Class Activation Maps for Weakly Supervised Object LocalizationCode0
Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization—0
DANet: Divergent Activation for Weakly Supervised Object LocalizationCode0
Information Entropy Based Feature Pooling for Convolutional Neural Networks—0
Multi-scale discriminative Region Discovery for Weakly-Supervised Object Localization—0
Dual-attention Focused Module for Weakly Supervised Object Localization—0
Weakly Supervised Localization Using Background Images—0
Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A SurveyCode0
Attention-based Dropout Layer for Weakly Supervised Object LocalizationCode0
Min-max Entropy for Weakly Supervised Pointwise LocalizationCode1
Show:102550
← PrevPage 11 of 14Next →

No leaderboard results yet.