Taylor Outlier Exposure
This addresses a practical problem for machine learning practitioners by enabling more cost-effective and scalable OOD detection without requiring clean outlier datasets.
The paper tackles the challenge of training Out-of-Distribution (OOD) detection models with noisy auxiliary datasets contaminated by in-distribution samples, proposing Taylor Outlier Exposure (TaylorOE) to regularize this noise and consistently outperform conventional methods in experiments.
Out-of-distribution (OOD) detection is the task of identifying data sampled from distributions that were not used during training. This task is essential for reliable machine learning and a better understanding of their generalization capabilities. Among OOD detection methods, Outlier Exposure (OE) significantly enhances OOD detection performance and generalization ability by exposing auxiliary OOD data to the model. However, constructing clean auxiliary OOD datasets, uncontaminated by in-distribution (ID) samples, is essential for OE; generally, a noisy OOD dataset contaminated with ID samples negatively impacts OE training dynamics and final detection performance. Furthermore, as dataset scale increases, constructing clean OOD data becomes increasingly challenging and costly. To address these challenges, we propose Taylor Outlier Exposure (TaylorOE), an OE-based approach with regularization that allows training on noisy OOD datasets contaminated with ID samples. Specifically, we represent the OE regularization term as a polynomial function via a Taylor expansion, allowing us to control the regularization strength for ID data in the auxiliary OOD dataset by adjusting the order of Taylor expansion. In our experiments on the OOD detection task with clean and noisy OOD datasets, we demonstrate that the proposed method consistently outperforms conventional methods and analyze our regularization term to show its effectiveness. Our implementation code of TaylorOE is available at \url{https://github.com/fukuchan41/TaylorOE}.