no code implementations • 28 Sep 2022 • Jingyun Jia, Philip K. Chan
In the first stage, we introduce a self-supervised feature decoupling method that finds the content features of the input samples from the known classes.
no code implementations • 13 May 2022 • Jingyun Jia, Philip K. Chan
In this paper, we introduce a self-supervised pre-training approach for the OSR problem in malware classification.
no code implementations • 28 May 2021 • Jingyun Jia, Philip K. Chan
The objective of Open set recognition (OSR) is to learn a classifier that can reject the unknown samples while classifying the known classes accurately.
1 code implementation • 26 Jun 2020 • Jingyun Jia, Philip K. Chan
Our contributions include: First, we introduce an extension that can be incorporated into different loss functions to find more discriminative representations.
3 code implementations • 12 Feb 2018 • Mehadi Hassen, Philip K. Chan
Open set recognition problems exist in many domains.