Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection
This work addresses the generalization issue in out-of-distribution detection for machine learning practitioners, but it is incremental as it builds upon existing feature-shaping methods.
The paper tackled the problem of limited generalization in feature-shaping methods for out-of-distribution detection by formulating an optimization framework and deriving a closed-form solution using only in-distribution data, resulting in improved generalization across diverse datasets and model architectures.
Feature shaping refers to a family of methods that exhibit state-of-the-art performance for out-of-distribution (OOD) detection. These approaches manipulate the feature representation, typically from the penultimate layer of a pre-trained deep learning model, so as to better differentiate between in-distribution (ID) and OOD samples. However, existing feature-shaping methods usually employ rules manually designed for specific model architectures and OOD datasets, which consequently limit their generalization ability. To address this gap, we first formulate an abstract optimization framework for studying feature-shaping methods. We then propose a concrete reduction of the framework with a simple piecewise constant shaping function and show that existing feature-shaping methods approximate the optimal solution to the concrete optimization problem. Further, assuming that OOD data is inaccessible, we propose a formulation that yields a closed-form solution for the piecewise constant shaping function, utilizing solely the ID data. Through extensive experiments, we show that the feature-shaping function optimized by our method improves the generalization ability of OOD detection across a large variety of datasets and model architectures.