2 papers
stat.ML2025
Perturbations in the Orthogonal Complement Subspace for Efficient Out-of-Distribution Detection
Zhexiao Huang, Weihao He, Shutao Deng +4
Out-of-distribution (OOD) detection is essential for deploying deep learning models in open-world environments. Existing approaches, such as energy-based scoring and gradient-proje…
cs.CV2024
Continual Novel Class Discovery via Feature Enhancement and Adaptation
Yifan Yu, Shaokun Wang, Yuhang He +2
Continual Novel Class Discovery (CNCD) aims to continually discover novel classes without labels while maintaining the recognition capability for previously learned classes. The ma…