Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2311.04095 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915874661728256 |
|---|---|
| author | Qin, Jianjian Zhang, Chao Gu, Chunzhi Wang, Zi Yu, Jun Wei, Yijin Xiao, Hui Yu, Xin |
| author_facet | Qin, Jianjian Zhang, Chao Gu, Chunzhi Wang, Zi Yu, Jun Wei, Yijin Xiao, Hui Yu, Xin |
| contents | We present PD-REAL, a novel large-scale dataset for unsupervised anomaly detection (AD) in the 3D domain. It is motivated by the fact that 2D-only representations in the AD task may fail to capture the geometric structures of anomalies due to uncertainty in lighting conditions or shooting angles. PD-REAL consists entirely of Play-Doh models for 15 object categories and focuses on the analysis of potential benefits from 3D information in a controlled environment. Specifically, objects are first created with six types of anomalies, such as \textit{dent}, \textit{crack}, or \textit{perforation}, and then photographed under different lighting conditions to mimic real-world inspection scenarios. To demonstrate the usefulness of 3D information, we use a commercially available RealSense camera to capture RGB and depth images. Compared to the existing 3D dataset for AD tasks, the data acquisition of PD-REAL is significantly cheaper, easily scalable, and easier to control variables. Furthermore, we introduce a multi-scale teacher--student framework with hierarchical distillation for multimodal anomaly detection. This architecture overcomes the inherent limitation of single-scale distillation approaches, which often struggle to reconcile global context with local features. Leveraging multi-level guidance from the teacher network, the student network can effectively capture richer features for anomaly detection. Extensive evaluations with our method and state-of-the-art AD algorithms on our dataset qualitatively and quantitatively demonstrate the higher detection accuracy of our method. Our dataset can be downloaded from https://github.com/Andy-cs008/PD-REAL |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_04095 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Multi-Scale Distillation for RGB-D Anomaly Detection on the PD-REAL Dataset Qin, Jianjian Zhang, Chao Gu, Chunzhi Wang, Zi Yu, Jun Wei, Yijin Xiao, Hui Yu, Xin Computer Vision and Pattern Recognition We present PD-REAL, a novel large-scale dataset for unsupervised anomaly detection (AD) in the 3D domain. It is motivated by the fact that 2D-only representations in the AD task may fail to capture the geometric structures of anomalies due to uncertainty in lighting conditions or shooting angles. PD-REAL consists entirely of Play-Doh models for 15 object categories and focuses on the analysis of potential benefits from 3D information in a controlled environment. Specifically, objects are first created with six types of anomalies, such as \textit{dent}, \textit{crack}, or \textit{perforation}, and then photographed under different lighting conditions to mimic real-world inspection scenarios. To demonstrate the usefulness of 3D information, we use a commercially available RealSense camera to capture RGB and depth images. Compared to the existing 3D dataset for AD tasks, the data acquisition of PD-REAL is significantly cheaper, easily scalable, and easier to control variables. Furthermore, we introduce a multi-scale teacher--student framework with hierarchical distillation for multimodal anomaly detection. This architecture overcomes the inherent limitation of single-scale distillation approaches, which often struggle to reconcile global context with local features. Leveraging multi-level guidance from the teacher network, the student network can effectively capture richer features for anomaly detection. Extensive evaluations with our method and state-of-the-art AD algorithms on our dataset qualitatively and quantitatively demonstrate the higher detection accuracy of our method. Our dataset can be downloaded from https://github.com/Andy-cs008/PD-REAL |
| title | Multi-Scale Distillation for RGB-D Anomaly Detection on the PD-REAL Dataset |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.04095 |