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
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information EstimatorCode0
Improve CAM with Auto-adapted Segmentation and Co-supervised Augmentation—0
Combinational Class Activation Maps for Weakly Supervised Object LocalizationCode0
Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization—0
Information Entropy Based Feature Pooling for Convolutional Neural Networks—0
DANet: Divergent Activation for Weakly Supervised Object LocalizationCode0
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
Show:102550
← PrevPage 11 of 14Next →

No leaderboard results yet.