Search Results for author: Qiankun Ma

Found 1 papers, 0 papers with code

Rethinking Safe Semi-supervised Learning: Transferring the Open-set Problem to A Close-set One

no code implementations ICCV 2023 Qiankun Ma, Jiyao Gao, Bo Zhan, Yunpeng Guo, Jiliu Zhou, Yan Wang

Conventional semi-supervised learning (SSL) lies in the close-set assumption that the labeled and unlabeled sets contain data with the same seen classes, called in-distribution (ID) data.

Cannot find the paper you are looking for? You can Submit a new open access paper.