Deep Metric Learning-Based Out-of-Distribution Detection with Synthetic Outlier Exposure

TL;DR

This paper introduces a novel OOD detection method combining deep metric learning with synthetic outlier data generated by diffusion models, significantly improving detection performance over existing methods.

Contribution

The paper proposes a new approach that uses diffusion models to generate synthetic OOD data and integrates metric learning, enhancing out-of-distribution detection capabilities.

Findings

Metric learning loss functions outperform softmax in OOD detection

Training with synthetic OOD data improves baseline model performance

Proposed method surpasses strong baselines in OOD detection metrics

Abstract

In this paper, we present a novel approach that combines deep metric learning and synthetic data generation using diffusion models for out-of-distribution (OOD) detection. One popular approach for OOD detection is outlier exposure, where models are trained using a mixture of in-distribution (ID) samples and ``seen" OOD samples. For the OOD samples, the model is trained to minimize the KL divergence between the output probability and the uniform distribution while correctly classifying the in-distribution (ID) data. In this paper, we propose a label-mixup approach to generate synthetic OOD data using Denoising Diffusion Probabilistic Models (DDPMs). Additionally, we explore recent advancements in metric learning to train our models. In the experiments, we found that metric learning-based loss functions perform better than the softmax. Furthermore, the baseline models (including softmax, and metric learning) show a significant improvement when trained with the generated OOD data. Our approach outperforms strong baselines in conventional OOD detection metrics.