The University of Southampton
University of Southampton Institutional Repository

MultiADS: defect-aware supervision for multi-type anomaly detection and segmentation in zero-shot learning

MultiADS: defect-aware supervision for multi-type anomaly detection and segmentation in zero-shot learning
MultiADS: defect-aware supervision for multi-type anomaly detection and segmentation in zero-shot learning
Precise optical inspection in industrial applications is crucial for minimizing scrap rates and reducing the associated costs. Besides merely detecting if a product is anomalous or not, it is crucial to know the distinct type of defect, such as a bent, cut, or scratch. The ability to recognize the "exact" defect type enables automated treatments of the anomalies in modern production lines. Current methods are limited to solely detecting whether a product is defective or not without providing any insights on the defect type, nevertheless detecting and identifying multiple defects. We propose MultiADS, a zero-shot learning approach, able to perform Multi-type Anomaly Detection and Segmentation. The architecture of MultiADS comprises CLIP and extra linear layers to align the visual- and textual representation in a joint feature space. To the best of our knowledge, our proposal, is the first approach to perform a multi-type anomaly segmentation task in zero-shot learning. Contrary to the other baselines, our approach i) generates specific anomaly masks for each distinct defect type, ii) learns to distinguish defect types, and iii) simultaneously identifies multiple defect types present in an anomalous product. Additionally, our approach outperforms zero/few-shot learning SoTA methods on image-level and pixel-level anomaly detection and segmentation tasks on five commonly used datasets: MVTec-AD, Visa, MPDD, MAD and Real-IAD.
Sadikaj, Ylli
eb267cce-5c6e-44b9-aafe-25102bed29b7
Zhou, Hongkuan
4d7462bb-31e9-4b4b-8685-64e118034d8a
Halilaj, Lavdim
010e7fdd-8b96-466f-8712-7e18d3386bca
Schmid, Stefan
5ed75bbb-b268-4244-9ebd-9d289c9fbd73
Staab, Steffen
bf48d51b-bd11-4d58-8e1c-4e6e03b30c49
Plant, Claudia
2b61a798-ea13-492a-a521-9563f2b7f135
Sadikaj, Ylli
eb267cce-5c6e-44b9-aafe-25102bed29b7
Zhou, Hongkuan
4d7462bb-31e9-4b4b-8685-64e118034d8a
Halilaj, Lavdim
010e7fdd-8b96-466f-8712-7e18d3386bca
Schmid, Stefan
5ed75bbb-b268-4244-9ebd-9d289c9fbd73
Staab, Steffen
bf48d51b-bd11-4d58-8e1c-4e6e03b30c49
Plant, Claudia
2b61a798-ea13-492a-a521-9563f2b7f135

Sadikaj, Ylli, Zhou, Hongkuan, Halilaj, Lavdim, Schmid, Stefan, Staab, Steffen and Plant, Claudia (2025) MultiADS: defect-aware supervision for multi-type anomaly detection and segmentation in zero-shot learning. International Conference on Computer Vision, , Honolulu, United States. 19 - 23 Oct 2025. 32 pp .

Record type: Conference or Workshop Item (Paper)

Abstract

Precise optical inspection in industrial applications is crucial for minimizing scrap rates and reducing the associated costs. Besides merely detecting if a product is anomalous or not, it is crucial to know the distinct type of defect, such as a bent, cut, or scratch. The ability to recognize the "exact" defect type enables automated treatments of the anomalies in modern production lines. Current methods are limited to solely detecting whether a product is defective or not without providing any insights on the defect type, nevertheless detecting and identifying multiple defects. We propose MultiADS, a zero-shot learning approach, able to perform Multi-type Anomaly Detection and Segmentation. The architecture of MultiADS comprises CLIP and extra linear layers to align the visual- and textual representation in a joint feature space. To the best of our knowledge, our proposal, is the first approach to perform a multi-type anomaly segmentation task in zero-shot learning. Contrary to the other baselines, our approach i) generates specific anomaly masks for each distinct defect type, ii) learns to distinguish defect types, and iii) simultaneously identifies multiple defect types present in an anomalous product. Additionally, our approach outperforms zero/few-shot learning SoTA methods on image-level and pixel-level anomaly detection and segmentation tasks on five commonly used datasets: MVTec-AD, Visa, MPDD, MAD and Real-IAD.

Text
2504.06740v2 - Author's Original
Download (55MB)

More information

Published date: October 2025
Venue - Dates: International Conference on Computer Vision, , Honolulu, United States, 2025-10-19 - 2025-10-23

Identifiers

Local EPrints ID: 503756
URI: http://eprints.soton.ac.uk/id/eprint/503756
PURE UUID: 9f6053f6-30bf-4861-a42c-4c066ff9af9d
ORCID for Steffen Staab: ORCID iD orcid.org/0000-0002-0780-4154

Catalogue record

Date deposited: 12 Aug 2025 17:02
Last modified: 22 Aug 2025 02:13

Export record

Contributors

Author: Ylli Sadikaj
Author: Hongkuan Zhou
Author: Lavdim Halilaj
Author: Stefan Schmid
Author: Steffen Staab ORCID iD
Author: Claudia Plant

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×