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 objectives, energy losses, or gradient-conflict control. We show that these training mechanisms can obscure a simpler issue: frozen long-tailed representations may already contain useful …