Dual-Adapter: Training-free Dual Adaptation for Few-shot Out-of-Distribution Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Xinyi, Li, Yaohui, Chen, Haoxing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910459191361536
author Chen, Xinyi
Li, Yaohui
Chen, Haoxing
author_facet Chen, Xinyi
Li, Yaohui
Chen, Haoxing
contents We study the problem of few-shot out-of-distribution (OOD) detection, which aims to detect OOD samples from unseen categories during inference time with only a few labeled in-domain (ID) samples. Existing methods mainly focus on training task-aware prompts for OOD detection. However, training on few-shot data may cause severe overfitting and textual prompts alone may not be enough for effective detection. To tackle these problems, we propose a prior-based Training-free Dual Adaptation method (Dual-Adapter) to detect OOD samples from both textual and visual perspectives. Specifically, Dual-Adapter first extracts the most significant channels as positive features and designates the remaining less relevant channels as negative features. Then, it constructs both a positive adapter and a negative adapter from a dual perspective, thereby better leveraging previously outlooked or interfering features in the training dataset. In this way, Dual-Adapter can inherit the advantages of CLIP not having to train, but also excels in distinguishing between ID and OOD samples. Extensive experimental results on four benchmark datasets demonstrate the superiority of Dual-Adapter.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16146
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dual-Adapter: Training-free Dual Adaptation for Few-shot Out-of-Distribution Detection
Chen, Xinyi
Li, Yaohui
Chen, Haoxing
Computer Vision and Pattern Recognition
We study the problem of few-shot out-of-distribution (OOD) detection, which aims to detect OOD samples from unseen categories during inference time with only a few labeled in-domain (ID) samples. Existing methods mainly focus on training task-aware prompts for OOD detection. However, training on few-shot data may cause severe overfitting and textual prompts alone may not be enough for effective detection. To tackle these problems, we propose a prior-based Training-free Dual Adaptation method (Dual-Adapter) to detect OOD samples from both textual and visual perspectives. Specifically, Dual-Adapter first extracts the most significant channels as positive features and designates the remaining less relevant channels as negative features. Then, it constructs both a positive adapter and a negative adapter from a dual perspective, thereby better leveraging previously outlooked or interfering features in the training dataset. In this way, Dual-Adapter can inherit the advantages of CLIP not having to train, but also excels in distinguishing between ID and OOD samples. Extensive experimental results on four benchmark datasets demonstrate the superiority of Dual-Adapter.
title Dual-Adapter: Training-free Dual Adaptation for Few-shot Out-of-Distribution Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.16146