OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Jingyang, Yang, Jingkang, Wang, Pengyun, Wang, Haoqi, Lin, Yueqian, Zhang, Haoran, Sun, Yiyou, Du, Xuefeng, Li, Yixuan, Liu, Ziwei, Chen, Yiran, Li, Hai
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910747841265664
author Zhang, Jingyang
Yang, Jingkang
Wang, Pengyun
Wang, Haoqi
Lin, Yueqian
Zhang, Haoran
Sun, Yiyou
Du, Xuefeng
Li, Yixuan
Liu, Ziwei
Chen, Yiran
Li, Hai
author_facet Zhang, Jingyang
Yang, Jingkang
Wang, Pengyun
Wang, Haoqi
Lin, Yueqian
Zhang, Haoran
Sun, Yiyou
Du, Xuefeng
Li, Yixuan
Liu, Ziwei
Chen, Yiran
Li, Hai
contents Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems. Despite the emergence of an increasing number of OOD detection methods, the evaluation inconsistencies present challenges for tracking the progress in this field. OpenOOD v1 initiated the unification of the OOD detection evaluation but faced limitations in scalability and scope. In response, this paper presents OpenOOD v1.5, a significant improvement from its predecessor that ensures accurate and standardized evaluation of OOD detection methodologies at large scale. Notably, OpenOOD v1.5 extends its evaluation capabilities to large-scale data sets (ImageNet) and foundation models (e.g., CLIP and DINOv2), and expands its scope to investigate full-spectrum OOD detection which considers semantic and covariate distribution shifts at the same time. This work also contributes in-depth analysis and insights derived from comprehensive experimental results, thereby enriching the knowledge pool of OOD detection methodologies. With these enhancements, OpenOOD v1.5 aims to drive advancements and offer a more robust and comprehensive evaluation benchmark for OOD detection research.
format Preprint
id arxiv_https___arxiv_org_abs_2306_09301
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
Zhang, Jingyang
Yang, Jingkang
Wang, Pengyun
Wang, Haoqi
Lin, Yueqian
Zhang, Haoran
Sun, Yiyou
Du, Xuefeng
Li, Yixuan
Liu, Ziwei
Chen, Yiran
Li, Hai
Machine Learning
Computer Vision and Pattern Recognition
Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems. Despite the emergence of an increasing number of OOD detection methods, the evaluation inconsistencies present challenges for tracking the progress in this field. OpenOOD v1 initiated the unification of the OOD detection evaluation but faced limitations in scalability and scope. In response, this paper presents OpenOOD v1.5, a significant improvement from its predecessor that ensures accurate and standardized evaluation of OOD detection methodologies at large scale. Notably, OpenOOD v1.5 extends its evaluation capabilities to large-scale data sets (ImageNet) and foundation models (e.g., CLIP and DINOv2), and expands its scope to investigate full-spectrum OOD detection which considers semantic and covariate distribution shifts at the same time. This work also contributes in-depth analysis and insights derived from comprehensive experimental results, thereby enriching the knowledge pool of OOD detection methodologies. With these enhancements, OpenOOD v1.5 aims to drive advancements and offer a more robust and comprehensive evaluation benchmark for OOD detection research.
title OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2306.09301