paper-with-me

Papers

Enhancing Outlier Knowledge for Few-Shot Out-of-Distribution Detection with Extensible Local Prompts

2024-09-07 · Fanhu Zeng, Zhen Cheng, Fei Zhu, Xu-Yao Zhang

Out-of-Distribution (OOD) detection, aiming to distinguish outliers from known categories, has gained prominence in practical scenarios. Recently, the advent of vision-language models (VLM) has heightened interest in enhancing OOD detection for VLM through few-shot tuning. However, existing methods mainly focus on optimizing global prompts, ignoring refined utilization of local information with regard to outliers. Motivated by this, we freeze global prompts and introduce a novel coarse-to-fine tuning paradigm to emphasize regional enhancement with local prompts. Our method comprises two integral components: global prompt guided negative augmentation and local prompt enhanced regional regularization. The former utilizes frozen, coarse global prompts as guiding cues to incorporate negative augmentation, thereby leveraging local outlier knowledge. The latter employs trainable local prompts and a regional regularization to capture local information effectively, aiding in outlier identification. We also propose regional-related metric to empower the enrichment of OOD detection. Moreover, since our approach explores enhancing local prompts only, it can be seamlessly integrated with trained global prompts during inference to boost the performance. Comprehensive experiments demonstrate the effectiveness and potential of our method. Notably, our method reduces average FPR95 by 5.17% against state-of-the-art method in 4-shot tuning on challenging ImageNet-1k dataset, even outperforming 16-shot results of previous methods.

📄 PDF Abstract BibTeX arXiv:2409.04796

Code (0)

등록된 구현이 없습니다.

Tasks

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

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Zero-Shot Out-of-Distribution Detection with Outlier Label Exposure

2024-06-03 · Choubo Ding, Guansong Pang

As vision-language models like CLIP are widely applied to zero-shot tasks and gain remarkable performance on in-distribution (ID) data, detecting and rejecting out-of-distribution (OOD) inputs in the zero-shot setting ha…

Out-of-Distribution Detection

Enhancing OOD Detection Using Latent Diffusion

2024-06-24 · Heng Gao, Zhuolin He, Jian Pu

Numerous Out-of-Distribution (OOD) detection algorithms have been developed to identify unknown samples or objects in real-world deployments. One line of work related to OOD detection propose utilizing auxiliary datasets…

Contrastive LearningKnowledge DistillationMetric LearningOut of Distribution (OOD) Detection

EOL: Transductive Few-Shot Open-Set Recognition by Enhancing Outlier Logits

2024-08-04 · Mateusz Ochal, Massimiliano Patacchiola, Malik Boudiaf, Sen Wang

In Few-Shot Learning (FSL), models are trained to recognise unseen objects from a query set, given a few labelled examples from a support set. In standard FSL, models are evaluated on query instances sampled from the sam…

Few-Shot LearningOpen Set LearningOutlier DetectionPseudo Label

ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection

2023-11-26 · CVPR 2024 1 · Yichen Bai, Zongbo Han, Changqing Zhang, Bing Cao 외

Out-of-distribution (OOD) detection methods often exploit auxiliary outliers to train model identifying OOD samples, especially discovering challenging outliers from auxiliary outliers dataset to improve OOD detection. H…

Few-Shot LearningOut-of-Distribution DetectionOut of Distribution (OOD) DetectionPrompt Learning

Vision Also You Need: Navigating Out-of-Distribution Detection with Multimodal Large Language Model

2026-01-20 · Haoran Xu, Yanlin Liu, Zizhao Tong, Jiaze Li 외 arxiv

Out-of-Distribution (OOD) detection is a critical task that has garnered significant attention. The emergence of CLIP has spurred extensive research into zero-shot OOD detection, often employing a training-free approach.…

Out-of-Distribution DetectionMultimodal ReasoningOutlier Detection