A Multi-dimensional Semantic Surprise Framework Based on Low-Entropy Semantic Manifolds for Fine-Grained Out-of-Distribution Detection

📝 Original Info

• Title: A Multi-dimensional Semantic Surprise Framework Based on Low-Entropy Semantic Manifolds for Fine-Grained Out-of-Distribution Detection
• ArXiv ID: 2510.13093
• Date: 2025-10-15
• Authors: Ningkang Peng, Yuzhe Mao, Yuhao Zhang, Linjin Qian, Qianfeng Yu, Yanhui Gu, Yi Chen, Li Kong

📝 Abstract

💡 Deep Analysis

Deep Dive into A Multi-dimensional Semantic Surprise Framework Based on Low-Entropy Semantic Manifolds for Fine-Grained Out-of-Distribution Detection.

Abstract analysis pending.

📄 Full Content

Reference