2 papers
cs.CV2026
Is Complex Training Necessary for Long-Tailed OOD Detection? A Re-think from Feature Geometry
Ningkang Peng, Xuanming Chen, Yanhui Gu
Long-tailed out-of-distribution (LT-OOD) detection is often addressed with specialized training, including auxiliary out-of-distribution (OOD) data, abstention heads, contrastive o…
cs.LG2023
Feature Noise Boosts DNN Generalization under Label Noise
Lu Zeng, Xuan Chen, Xiaoshuang Shi +1
The presence of label noise in the training data has a profound impact on the generalization of deep neural networks (DNNs). In this study, we introduce and theoretically demonstra…