1 code implementation • Elsevier Computer Networks Journal 2023 • Thilini Dahanayaka, Yasod Ginige, Yi Huang, Guillaume Jourjon, Suranga Seneviratne
First, we show that a well-regularized deep learning model improves the open-set classification and then we propose a novel open-set classification method with three variants that perform consistently over multiple datasets.
no code implementations • 28 Mar 2023 • Teng-Hui Huang, Thilini Dahanayaka, Kanchana Thilakarathna, Philip H. W. Leong, Hesham El Gamal
Our information-theoretic approach can be extended to supervised and semi-supervised settings with straightforward derivations.