Discriminative Complementary-Label Learning with Weighted LossDownload PDFOpen Website

Published: 01 Jan 2021, Last Modified: 31 Jan 2024ICML 2021Readers: Everyone
Abstract: Complementary-label learning (CLL) deals with the weak supervision scenario where each training instance is associated with one \emph{complementary} label, which specifies the class label that the ...
0 Replies

Loading