Visual anomaly classification and segmentation are vital for automating industrial quality
inspection. The focus of prior research in the field has been on training custom models for …

This paper considers zero-shot Anomaly Detection (AD), a valuable yet under-studied task,
which performs AD without any reference images of the test objects. Specifically, we employ …

Recent advancements in large-scale visual-language pre-trained models have led to
significant progress in zero-/few-shot anomaly detection within natural image domains …

Zero-shot anomaly detection (ZSAD) requires detection models trained using auxiliary data
to detect anomalies without any training sample in a target dataset. It is a crucial task when …

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 …

Zero-shot detection, namely, localizing both seen and unseen objects, increasingly gains
importance for large-scale applications, with large number of object classes, since …

We present a novel framework, ie, Segment Any Anomaly+(SAA+), for zero-shot anomaly
segmentation with hybrid prompt regularization to improve the adaptability of modern …

We address the problem of anomaly detection in videos. The goal is to identify unusual
behaviours automatically by learning exclusively from normal videos. Most existing …

Large Vision-Language Models (LVLMs) such as MiniGPT-4 and LLaVA have demonstrated
the capability of understanding images and achieved remarkable performance in various …

Abstract Out-of-distribution (OOD) detection refers to training the model on in-distribution (ID)
dataset to classify if the input images come from unknown classes. Considerable efforts …