paper-with-me

홈 › Papers

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

2024-05-25 · Xinyi Chen, Yaohui Li, Haoxing Chen

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.

📄 PDF Abstract BibTeX arXiv:2405.16146

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution DetectionOut of Distribution (OOD) Detection

Methods 이 논문이 사용한 방법론

Adapter 설명 없음
Focus 설명 없음
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Prompt-Free and Efficient SAM2 Adaptation for Biomedical Semantic Segmentation via Dual Adapters

2026-05-07 · Hinako Mitsuoka, Kazuhiro Hotta arxiv

Segment Anything Model 2 (SAM2) demonstrated impressive zero-shot capabilities on natural images but faces challenges in biomedical segmentation due to significant domain shifts and prompt dependency. To address these li…

parameter-efficient fine-tuningSemantic Segmentation

Token-Level Adaptation of LoRA Adapters for Downstream Task Generalization

2023-11-17 · Joshua Belofsky

This paper introduces a method for adapting LoRA adapters in smaller-sized language models to arbitrary downstream tasks. Unlike standard mixture-of-expert architectures, our method employs a gradient-free routing functi…

ARCGSM8KReading Comprehension

Improving Robustness of Foundation Models in Domain Adaptation with Soup-Adapters

2025-07-08 · Marco Roschkowski arxiv

In this paper, we tackle two fundamental problems in few-shot domain adaptation of foundation models. First, hyperparameter tuning is often impractical due to the lack of large validation datasets. Second, model robustne…

Domain Adaptation

CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning

2025-05-30 · CVPR 2025 1 · Jiangpeng He, Zhihao Duan, Fengqing Zhu

Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes. Recently, pre-trained models (PTMs) combined with parameter-efficient fine-tuning (PEFT…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+2

SCALE-LoRA: Auditing Post-Retrieval LoRA Composition with Residual Merging and View Reliability

2026-05-02 · Shuaipeng Zhou, Yu Zhang arxiv

Libraries of Low-Rank Adaptation (LoRA) adapters are becoming a practical by-product of parameter-efficient adaptation. Once such adapters accumulate, a natural question is no longer how to train one adapter for one task…