Saved in:
Bibliographic Details
Main Authors: Liu, Yibing, Tian, Chris Xing, Li, Haoliang, Ma, Lei, Wang, Shiqi
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.02879
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910359824105472
author Liu, Yibing
Tian, Chris Xing
Li, Haoliang
Ma, Lei
Wang, Shiqi
author_facet Liu, Yibing
Tian, Chris Xing
Li, Haoliang
Ma, Lei
Wang, Shiqi
contents The out-of-distribution (OOD) problem generally arises when neural networks encounter data that significantly deviates from the training data distribution, i.e., in-distribution (InD). In this paper, we study the OOD problem from a neuron activation view. We first formulate neuron activation states by considering both the neuron output and its influence on model decisions. Then, to characterize the relationship between neurons and OOD issues, we introduce the \textit{neuron activation coverage} (NAC) -- a simple measure for neuron behaviors under InD data. Leveraging our NAC, we show that 1) InD and OOD inputs can be largely separated based on the neuron behavior, which significantly eases the OOD detection problem and beats the 21 previous methods over three benchmarks (CIFAR-10, CIFAR-100, and ImageNet-1K). 2) a positive correlation between NAC and model generalization ability consistently holds across architectures and datasets, which enables a NAC-based criterion for evaluating model robustness. Compared to prevalent InD validation criteria, we show that NAC not only can select more robust models, but also has a stronger correlation with OOD test performance.
format Preprint
id arxiv_https___arxiv_org_abs_2306_02879
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization
Liu, Yibing
Tian, Chris Xing
Li, Haoliang
Ma, Lei
Wang, Shiqi
Machine Learning
The out-of-distribution (OOD) problem generally arises when neural networks encounter data that significantly deviates from the training data distribution, i.e., in-distribution (InD). In this paper, we study the OOD problem from a neuron activation view. We first formulate neuron activation states by considering both the neuron output and its influence on model decisions. Then, to characterize the relationship between neurons and OOD issues, we introduce the \textit{neuron activation coverage} (NAC) -- a simple measure for neuron behaviors under InD data. Leveraging our NAC, we show that 1) InD and OOD inputs can be largely separated based on the neuron behavior, which significantly eases the OOD detection problem and beats the 21 previous methods over three benchmarks (CIFAR-10, CIFAR-100, and ImageNet-1K). 2) a positive correlation between NAC and model generalization ability consistently holds across architectures and datasets, which enables a NAC-based criterion for evaluating model robustness. Compared to prevalent InD validation criteria, we show that NAC not only can select more robust models, but also has a stronger correlation with OOD test performance.
title Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization
topic Machine Learning
url https://arxiv.org/abs/2306.02879