Towards Few-shot Out-of-Distribution Detection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Dong, Jiuqing, Gao, Yongbin, Zhou, Heng, Cen, Jun, Yao, Yifan, Yoon, Sook, Sun, Park Dong
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916110714011648
author Dong, Jiuqing
Gao, Yongbin
Zhou, Heng
Cen, Jun
Yao, Yifan
Yoon, Sook
Sun, Park Dong
author_facet Dong, Jiuqing
Gao, Yongbin
Zhou, Heng
Cen, Jun
Yao, Yifan
Yoon, Sook
Sun, Park Dong
contents Out-of-distribution (OOD) detection is critical for ensuring the reliability of open-world intelligent systems. Despite the notable advancements in existing OOD detection methodologies, our study identifies a significant performance drop under the scarcity of training samples. In this context, we introduce a novel few-shot OOD detection benchmark, carefully constructed to address this gap. Our empirical analysis reveals the superiority of ParameterEfficient Fine-Tuning (PEFT) strategies, such as visual prompt tuning and visual adapter tuning, over conventional techniques, including fully fine-tuning and linear probing tuning in the few-shot OOD detection task. Recognizing some crucial information from the pre-trained model, which is pivotal for OOD detection, may be lost during the fine-tuning process, we propose a method termed DomainSpecific and General Knowledge Fusion (DSGF). This approach is designed to be compatible with diverse fine-tuning frameworks. Our experiments show that the integration of DSGF significantly enhances the few-shot OOD detection capabilities across various methods and fine-tuning methodologies, including fully fine-tuning, visual adapter tuning, and visual prompt tuning. The code will be released.
format Preprint
id arxiv_https___arxiv_org_abs_2311_12076
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Towards Few-shot Out-of-Distribution Detection
Dong, Jiuqing
Gao, Yongbin
Zhou, Heng
Cen, Jun
Yao, Yifan
Yoon, Sook
Sun, Park Dong
Computer Vision and Pattern Recognition
Out-of-distribution (OOD) detection is critical for ensuring the reliability of open-world intelligent systems. Despite the notable advancements in existing OOD detection methodologies, our study identifies a significant performance drop under the scarcity of training samples. In this context, we introduce a novel few-shot OOD detection benchmark, carefully constructed to address this gap. Our empirical analysis reveals the superiority of ParameterEfficient Fine-Tuning (PEFT) strategies, such as visual prompt tuning and visual adapter tuning, over conventional techniques, including fully fine-tuning and linear probing tuning in the few-shot OOD detection task. Recognizing some crucial information from the pre-trained model, which is pivotal for OOD detection, may be lost during the fine-tuning process, we propose a method termed DomainSpecific and General Knowledge Fusion (DSGF). This approach is designed to be compatible with diverse fine-tuning frameworks. Our experiments show that the integration of DSGF significantly enhances the few-shot OOD detection capabilities across various methods and fine-tuning methodologies, including fully fine-tuning, visual adapter tuning, and visual prompt tuning. The code will be released.
title Towards Few-shot Out-of-Distribution Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.12076