CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveraging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ling, Zhiwei, Chang, Yachen, Zhao, Hailiang, Zhao, Xinkui, Chow, Kingsum, Deng, Shuiguang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910874888830976
author Ling, Zhiwei
Chang, Yachen
Zhao, Hailiang
Zhao, Xinkui
Chow, Kingsum
Deng, Shuiguang
author_facet Ling, Zhiwei
Chang, Yachen
Zhao, Hailiang
Zhao, Xinkui
Chow, Kingsum
Deng, Shuiguang
contents Deep neural networks (DNNs) have been widely criticized for their overconfidence when dealing with out-of-distribution (OOD) samples, highlighting the critical need for effective OOD detection to ensure the safe deployment of DNNs in real-world settings. Existing post-hoc OOD detection methods primarily enhance the discriminative power of logit-based approaches by reshaping sample features, yet they often neglect critical information inherent in the features themselves. In this paper, we propose the Class-Aware Relative Feature-based method (CARef), which utilizes the error between a sample's feature and its class-aware average feature as a discriminative criterion. To further refine this approach, we introduce the Class-Aware Decoupled Relative Feature-based method (CADRef), which decouples sample features based on the alignment of signs between the relative feature and corresponding model weights, enhancing the discriminative capabilities of CARef. Extensive experimental results across multiple datasets and models demonstrate that both proposed methods exhibit effectiveness and robustness in OOD detection compared to state-of-the-art methods. Specifically, our two methods outperform the best baseline by 2.82% and 3.27% in AUROC, with improvements of 4.03% and 6.32% in FPR95, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2503_00325
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveraging
Ling, Zhiwei
Chang, Yachen
Zhao, Hailiang
Zhao, Xinkui
Chow, Kingsum
Deng, Shuiguang
Computer Vision and Pattern Recognition
Deep neural networks (DNNs) have been widely criticized for their overconfidence when dealing with out-of-distribution (OOD) samples, highlighting the critical need for effective OOD detection to ensure the safe deployment of DNNs in real-world settings. Existing post-hoc OOD detection methods primarily enhance the discriminative power of logit-based approaches by reshaping sample features, yet they often neglect critical information inherent in the features themselves. In this paper, we propose the Class-Aware Relative Feature-based method (CARef), which utilizes the error between a sample's feature and its class-aware average feature as a discriminative criterion. To further refine this approach, we introduce the Class-Aware Decoupled Relative Feature-based method (CADRef), which decouples sample features based on the alignment of signs between the relative feature and corresponding model weights, enhancing the discriminative capabilities of CARef. Extensive experimental results across multiple datasets and models demonstrate that both proposed methods exhibit effectiveness and robustness in OOD detection compared to state-of-the-art methods. Specifically, our two methods outperform the best baseline by 2.82% and 3.27% in AUROC, with improvements of 4.03% and 6.32% in FPR95, respectively.
title CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveraging
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.00325