open set recognition (OSR) has been an emerging topic. Besides recognizing
predefined classes, the system needs to reject the unknowns. prototype learning
is a potential manner to handle the problem, as its abili
Proposing Open Margin Cosine Loss (OMCL) for open-set recognition in medical fields, this research paper introduces Margin Loss with Adaptive Scale (MLAS) and Open-Space Suppression (OSS) mechanisms to improve classification accuracy and performance.