Generalized out-of-distribution detection and beyond in vision language model era: A survey

A Miyai, J Yang, J Zhang, Y Ming, Y Lin, Q Yu… - arXiv preprint arXiv …, 2024 - arxiv.org
Detecting out-of-distribution (OOD) samples is crucial for ensuring the safety of machine
learning systems and has shaped the field of OOD detection. Meanwhile, several other …

Promptad: Learning prompts with only normal samples for few-shot anomaly detection

X Li, Z Zhang, X Tan, C Chen, Y Qu… - Proceedings of the …, 2024 - openaccess.thecvf.com
The vision-language model has brought great improvement to few-shot industrial anomaly
detection which usually needs to design of hundreds of prompts through prompt …

Adaclip: Adapting clip with hybrid learnable prompts for zero-shot anomaly detection

Y Cao, J Zhang, L Frittoli, Y Cheng, W Shen… - … on Computer Vision, 2025 - Springer
Zero-shot anomaly detection (ZSAD) targets the identification of anomalies within images
from arbitrary novel categories. This study introduces AdaCLIP for the ZSAD task, leveraging …

Do llms understand visual anomalies? uncovering llm capabilities in zero-shot anomaly detection

J Zhu, S Cai, F Deng, J Wu - arXiv preprint arXiv:2404.09654, 2024 - arxiv.org
Large vision-language models (LVLMs) are markedly proficient in deriving visual
representations guided by natural language. Recent explorations have utilized LVLMs to …

Attention-Guided Perturbation for Unsupervised Image Anomaly Detection

T Huang, Y Cheng, J Xia, R Yu, Y Cai, J Xiang… - arXiv preprint arXiv …, 2024 - arxiv.org
Reconstruction-based methods have significantly advanced modern unsupervised anomaly
detection. However, the strong capacity of neural networks often violates the underlying …

A Survey on RGB, 3D, and Multimodal Approaches for Unsupervised Industrial Anomaly Detection

Y Lin, Y Chang, X Tong, J Yu, A Liotta, G Huang… - arXiv preprint arXiv …, 2024 - arxiv.org
In the advancement of industrial informatization, Unsupervised Industrial Anomaly Detection
(UIAD) technology effectively overcomes the scarcity of abnormal samples and significantly …

Towards Efficient Pixel Labeling for Industrial Anomaly Detection and Localization

H Li, J Wu, LY Wu, H Chen, D Liu, C Shen - arXiv preprint arXiv …, 2024 - arxiv.org
In the realm of practical Anomaly Detection (AD) tasks, manual labeling of anomalous pixels
proves to be a costly endeavor. Consequently, many AD methods are crafted as one-class …

FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model

Y Li, E Ivanova, M Bruveris - arXiv preprint arXiv:2409.00556, 2024 - arxiv.org
Automatic image anomaly detection is important for quality inspection in the manufacturing
industry. The usual unsupervised anomaly detection approach is to train a model for each …

[PDF][PDF] Towards Better Zero-Shot Anomaly Detection under Distribution Shift with CLIP

J Gao, C He, L Duan, J Zuo - 2024 - bmva-archive.org.uk
Industrial anomaly detection is one of the important computer vision applications in the real
world, aiming at identifying anomalous products during testing. In this paper, we investigate …

Enhancing Visual Anomaly Detection with Auxiliary Information

Z Zhang - 2024 - era.library.ualberta.ca
This thesis delves into the advancements in visual anomaly detection (AD), a challenging
task in identifying outliers in images such as defects and lesions, which is crucial in many …