GROOD: GRadient-Aware Out-of-Distribution Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ElAraby, Mostafa, Sahoo, Sabyasachi, Pequignot, Yann, Novello, Paul, Paull, Liam
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916952342003712
author ElAraby, Mostafa
Sahoo, Sabyasachi
Pequignot, Yann
Novello, Paul
Paull, Liam
author_facet ElAraby, Mostafa
Sahoo, Sabyasachi
Pequignot, Yann
Novello, Paul
Paull, Liam
contents Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models in real-world applications. Existing methods typically focus on feature representations or output-space analysis, often assuming a distribution over these spaces or leveraging gradient norms with respect to model parameters. However, these approaches struggle to distinguish near-OOD samples and often require extensive hyper-parameter tuning, limiting their practicality.In this work, we propose GRadient-aware Out-Of-Distribution detection (GROOD), a method that derives an OOD prototype from synthetic samples and computes class prototypes directly from In-distribution (ID) training data. By analyzing the gradients of a nearest-class-prototype loss function concerning an artificial OOD prototype, our approach achieves a clear separation between in-distribution and OOD samples. Experimental evaluations demonstrate that gradients computed from the OOD prototype enhance the distinction between ID and OOD data, surpassing established baselines in robustness, particularly on ImageNet-1k. These findings highlight the potential of gradient-based methods and prototype-driven approaches in advancing OOD detection within deep neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2312_14427
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GROOD: GRadient-Aware Out-of-Distribution Detection
ElAraby, Mostafa
Sahoo, Sabyasachi
Pequignot, Yann
Novello, Paul
Paull, Liam
Computer Vision and Pattern Recognition
Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models in real-world applications. Existing methods typically focus on feature representations or output-space analysis, often assuming a distribution over these spaces or leveraging gradient norms with respect to model parameters. However, these approaches struggle to distinguish near-OOD samples and often require extensive hyper-parameter tuning, limiting their practicality.In this work, we propose GRadient-aware Out-Of-Distribution detection (GROOD), a method that derives an OOD prototype from synthetic samples and computes class prototypes directly from In-distribution (ID) training data. By analyzing the gradients of a nearest-class-prototype loss function concerning an artificial OOD prototype, our approach achieves a clear separation between in-distribution and OOD samples. Experimental evaluations demonstrate that gradients computed from the OOD prototype enhance the distinction between ID and OOD data, surpassing established baselines in robustness, particularly on ImageNet-1k. These findings highlight the potential of gradient-based methods and prototype-driven approaches in advancing OOD detection within deep neural networks.
title GROOD: GRadient-Aware Out-of-Distribution Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.14427