CVLGApr 18, 2024

Gradient-Regularized Out-of-Distribution Detection

arXiv:2404.12368v314 citationsh-index: 18Has CodeECCV
Originality Incremental advance
AI Analysis

This addresses the challenge of reliable OOD detection for neural networks in real-world applications, representing an incremental improvement over existing methods.

The paper tackles the problem of neural networks making overconfident errors on out-of-distribution (OOD) data by proposing a gradient-regularized method that exploits local information from an auxiliary dataset, improving the state-of-the-art FPR95 by 4% on ImageNet experiments.

One of the challenges for neural networks in real-life applications is the overconfident errors these models make when the data is not from the original training distribution. Addressing this issue is known as Out-of-Distribution (OOD) detection. Many state-of-the-art OOD methods employ an auxiliary dataset as a surrogate for OOD data during training to achieve improved performance. However, these methods fail to fully exploit the local information embedded in the auxiliary dataset. In this work, we propose the idea of leveraging the information embedded in the gradient of the loss function during training to enable the network to not only learn a desired OOD score for each sample but also to exhibit similar behavior in a local neighborhood around each sample. We also develop a novel energy-based sampling method to allow the network to be exposed to more informative OOD samples during the training phase. This is especially important when the auxiliary dataset is large. We demonstrate the effectiveness of our method through extensive experiments on several OOD benchmarks, improving the existing state-of-the-art FPR95 by 4% on our ImageNet experiment. We further provide a theoretical analysis through the lens of certified robustness and Lipschitz analysis to showcase the theoretical foundation of our work. Our code is available at https://github.com/o4lc/Greg-OOD.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes