UCDSC: Open Set UnCertainty aware Deep Simplex Classifier for Medical Image Datasets
Published in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026, 2026
A novel framework for Open-Set Recognition leveraging Neural Collapse and a custom loss function to penalize open-space regions, validated across five MedMNIST datasets.
Recommended citation: Arnav Aditya, Nitin Kumar, and Saurabh Shigwan. "UCDSC: Open Set UnCertainty aware Deep Simplex Classifier for Medical Image Datasets." In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 4787-4796. 2026.
Download Paper