Semi-Supervised Deep Learning with Memory

ECCV 2018 Yanbei ChenXiatian ZhuShaogang Gong

We consider the semi-supervised multi-class classification problem of learning from sparse labelled and abundant unlabelled training data. To address this problem, existing semi-supervised deep learning methods often rely on the up-to-date “network-in-training” to formulate the semi-supervised learning objective... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.