Feature Bank Enhancement for Distance-based Out-of-Distribution Detection
This addresses reliability issues in deep learning applications by improving OOD detection, but it is incremental as it builds on existing distance-based methods.
The paper tackled the problem of biased feature distributions in distance-based out-of-distribution detection, which limits performance by assigning low scores to in-distribution samples, and proposed Feature Bank Enhancement to constrain extreme features, achieving state-of-the-art results on ImageNet-1k and CIFAR-10 benchmarks.
Out-of-distribution (OOD) detection is critical to ensuring the reliability of deep learning applications and has attracted significant attention in recent years. A rich body of literature has emerged to develop efficient score functions that assign high scores to in-distribution (ID) samples and low scores to OOD samples, thereby helping distinguish OOD samples. Among these methods, distance-based score functions are widely used because of their efficiency and ease of use. However, deep learning often leads to a biased distribution of data features, and extreme features are inevitable. These extreme features make the distance-based methods tend to assign too low scores to ID samples. This limits the OOD detection capabilities of such methods. To address this issue, we propose a simple yet effective method, Feature Bank Enhancement (FBE), that uses statistical characteristics from dataset to identify and constrain extreme features to the separation boundaries, therapy making the distance between samples inside and outside the distribution farther. We conducted experiments on large-scale ImageNet-1k and CIFAR-10 respectively, and the results show that our method achieves state-of-the-art performance on both benchmark. Additionally, theoretical analysis and supplementary experiments are conducted to provide more insights into our method.