OOD Aware Supervised Contrastive Learning

TL;DR

This paper introduces an OOD detection method that enhances supervised contrastive learning by incorporating additional contrast terms and pseudo-OOD feature generation, achieving state-of-the-art results.

Contribution

It extends SupCon loss with new contrast terms and feature mixing techniques to improve OOD detection robustness without requiring auxiliary OOD data.

Findings

Achieves state-of-the-art OOD detection performance

Effective even without auxiliary OOD data

Simple and efficient extension of supervised contrastive learning

Abstract

Out-of-Distribution (OOD) detection is a crucial problem for the safe deployment of machine learning models identifying samples that fall outside of the training distribution, i.e. in-distribution data (ID). Most OOD works focus on the classification models trained with Cross Entropy (CE) and attempt to fix its inherent issues. In this work we leverage powerful representation learned with Supervised Contrastive (SupCon) training and propose a holistic approach to learn a classifier robust to OOD data. We extend SupCon loss with two additional contrast terms. The first term pushes auxiliary OOD representations away from ID representations without imposing any constraints on similarities among auxiliary data. The second term pushes OOD features far from the existing class prototypes, while pushing ID representations closer to their corresponding class prototype. When auxiliary OOD data is not available, we propose feature mixing techniques to efficiently generate pseudo-OOD features. Our solution is simple and efficient and acts as a natural extension of the closed-set supervised contrastive representation learning. We compare against different OOD detection methods on the common benchmarks and show state-of-the-art results.