Margin-bounded Confidence Scores for Out-of-Distribution Detection

TL;DR

This paper introduces Margin bounded Confidence Scores (MaCS), a simple yet effective method for out-of-distribution detection that improves the separation between ID and OOD samples by enlarging confidence score disparities.

Contribution

The paper proposes a novel constraint in OE-based classifiers to enhance OOD detection by increasing confidence score disparity, improving detection without sacrificing ID accuracy.

Findings

MaCS significantly outperforms state-of-the-art methods on benchmark datasets.

The method maintains high ID classification accuracy while improving OOD detection.

Extensive experiments validate the effectiveness of MaCS across various metrics.

Abstract

In many critical Machine Learning applications, such as autonomous driving and medical image diagnosis, the detection of out-of-distribution (OOD) samples is as crucial as accurately classifying in-distribution (ID) inputs. Recently Outlier Exposure (OE) based methods have shown promising results in detecting OOD inputs via model fine-tuning with auxiliary outlier data. However, most of the previous OE-based approaches emphasize more on synthesizing extra outlier samples or introducing regularization to diversify OOD sample space, which is rather unquantifiable in practice. In this work, we propose a novel and straightforward method called Margin bounded Confidence Scores (MaCS) to address the nontrivial OOD detection problem by enlarging the disparity between ID and OOD scores, which in turn makes the decision boundary more compact facilitating effective segregation with a simple threshold. Specifically, we augment the learning objective of an OE regularized classifier with a supplementary constraint, which penalizes high confidence scores for OOD inputs compared to that of ID and significantly enhances the OOD detection performance while maintaining the ID classification accuracy. Extensive experiments on various benchmark datasets for image classification tasks demonstrate the effectiveness of the proposed method by significantly outperforming state-of-the-art (S.O.T.A) methods on various benchmarking metrics. The code is publicly available at https://github.com/lakpa-tamang9/margin_ood