Zero-Shot Anomaly Detection with Pre-trained Segmentation Models

Matthew Baugh, James Batten, Johanna P. Müller, Bernhard Kainz
6/15/2023
cs.CVcs.LG

No confident code implementation found for this paper. 5 possible matches can be shown below.

Abstract

This technical report outlines our submission to the zero-shot track of the Visual Anomaly and Novelty Detection (VAND) 2023 Challenge. Building on the performance of the WINCLIP framework, we aim to enhance the system's localization capabilities by integrating zero-shot segmentation models. In addition, we perform foreground instance segmentation which enables the model to focus on the relevant parts of the image, thus allowing the models to better identify small or subtle deviations. Our pipeline requires no external data or information, allowing for it to be directly applied to new datasets. Our team (Variance Vigilance Vanguard) ranked third in the zero-shot track of the VAND challenge, and achieve an average F1-max score of 81.5/24.2 at a sample/pixel level on the VisA dataset.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 5 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors

86% match2026

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

86% match1 repo352024

MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images

85% match2 repos4392026

Enhancing Zero-Shot Anomaly Detection: CLIP-SAM Collaboration with Cascaded Prompts

85% match2025

On the Problem of Consistent Anomalies in Zero-Shot Anomaly Detection

85% match2025

AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2

83% match1 repo2602024

Cite this paper

@article{baugh2023zeroshot,
  title  = {Zero-Shot Anomaly Detection with Pre-trained Segmentation Models},
  author = {Matthew Baugh and James Batten and Johanna P. Müller and Bernhard Kainz},
  year   = {2023},
  eprint = {2306.09269},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.09269v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.09269.svg)](https://codeofpaper.com/paper/2306.09269)

Discussion