Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection

arXiv:2402.10062v1 Announce Type: new
Abstract: For a machine learning model deployed in real world scenarios, the ability of detecting out-of-distribution (OOD) samples is indispensable and challenging. Most existing OOD detection methods focused on exploring advanced training skills or training-free tricks to prevent the model from yielding overconfident confidence score for unknown samples. The training-based methods require expensive training cost and rely on OOD samples which are not always available, while most training-free methods can not efficiently utilize the prior information …

abstract advanced arxiv confidence cs.lg detection detection methods distribution free machine machine learning machine learning model neuron pruning samples skills stat.ml training tricks type world