2025
Unlocking Better Closed-Set Alignment Based on Neural Collapse for Open-Set Recognition
AAAI 2025technical
In recent Open-set Recognition (OSR) community, a prevailing belief is that enhancing the discriminative boundaries of closed-set classes can improve the robustness of Deep Neural Networks (DNNs) against open data during testing. Typical studies validate this *implicitly* by empirical evidence, with…