RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910536445198336 |
|---|---|
| author | Cheng, Yuqi Cao, Yunkang Chen, Rui Shen, Weiming |
| author_facet | Cheng, Yuqi Cao, Yunkang Chen, Rui Shen, Weiming |
| contents | Robustness against noisy imaging is crucial for practical image anomaly detection systems. This study introduces a Robust Anomaly Detection (RAD) dataset with free views, uneven illuminations, and blurry collections to systematically evaluate the robustness of current anomaly detection methods. Specifically, RAD aims to identify foreign objects on working platforms as anomalies. The collection process incorporates various sources of imaging noise, such as viewpoint changes, uneven illuminations, and blurry collections, to replicate real-world inspection scenarios. Subsequently, we assess and analyze 11 state-of-the-art unsupervised and zero-shot methods on RAD. Our findings indicate that: 1) Variations in viewpoint, illumination, and blurring affect anomaly detection methods to varying degrees; 2) Methods relying on memory banks and assisted by synthetic anomalies demonstrate stronger robustness; 3) Effectively leveraging the general knowledge of foundational models is a promising avenue for enhancing the robustness of anomaly detection methods. The dataset is available at https://github.com/hustCYQ/RAD-dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_07176 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detection Cheng, Yuqi Cao, Yunkang Chen, Rui Shen, Weiming Computer Vision and Pattern Recognition Robustness against noisy imaging is crucial for practical image anomaly detection systems. This study introduces a Robust Anomaly Detection (RAD) dataset with free views, uneven illuminations, and blurry collections to systematically evaluate the robustness of current anomaly detection methods. Specifically, RAD aims to identify foreign objects on working platforms as anomalies. The collection process incorporates various sources of imaging noise, such as viewpoint changes, uneven illuminations, and blurry collections, to replicate real-world inspection scenarios. Subsequently, we assess and analyze 11 state-of-the-art unsupervised and zero-shot methods on RAD. Our findings indicate that: 1) Variations in viewpoint, illumination, and blurring affect anomaly detection methods to varying degrees; 2) Methods relying on memory banks and assisted by synthetic anomalies demonstrate stronger robustness; 3) Effectively leveraging the general knowledge of foundational models is a promising avenue for enhancing the robustness of anomaly detection methods. The dataset is available at https://github.com/hustCYQ/RAD-dataset. |
| title | RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.07176 |