Universal Novelty Detection Through Adaptive Contrastive Learning

TL;DR

This paper introduces AutoAugOOD, a contrastive learning-based approach for universal novelty detection that adapts to various distribution shifts, outperforming existing methods across multiple image benchmarks.

Contribution

The paper proposes AutoAugOOD, a novel probabilistic auto-negative pair generation method combined with contrastive learning, enhancing universality and adaptability in novelty detection tasks.

Findings

AutoAugOOD outperforms existing methods under distribution shifts.

The method is effective across different novelty detection setups.

It demonstrates superior generalization on various image datasets.

Abstract

Novelty detection is a critical task for deploying machine learning models in the open world. A crucial property of novelty detection methods is universality, which can be interpreted as generalization across various distributions of training or test data. More precisely, for novelty detection, distribution shifts may occur in the training set or the test set. Shifts in the training set refer to cases where we train a novelty detector on a new dataset and expect strong transferability. Conversely, distribution shifts in the test set indicate the methods' performance when the trained model encounters a shifted test sample. We experimentally show that existing methods falter in maintaining universality, which stems from their rigid inductive biases. Motivated by this, we aim for more generalized techniques that have more adaptable inductive biases. In this context, we leverage the fact that contrastive learning provides an efficient framework to easily switch and adapt to new inductive biases through the proper choice of augmentations in forming the negative pairs. We propose a novel probabilistic auto-negative pair generation method AutoAugOOD, along with contrastive learning, to yield a universal novelty detector method. Our experiments demonstrate the superiority of our method under different distribution shifts in various image benchmark datasets. Notably, our method emerges universality in the lens of adaptability to different setups of novelty detection, including one-class, unlabeled multi-class, and labeled multi-class settings. Code: https://github.com/mojtaba-nafez/UNODE