Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.02263 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911903394037760 |
|---|---|
| author | Wang, Chengjie Zhu, Haokun Peng, Jinlong Wang, Yue Yi, Ran Wu, Yunsheng Ma, Lizhuang Zhang, Jiangning |
| author_facet | Wang, Chengjie Zhu, Haokun Peng, Jinlong Wang, Yue Yi, Ran Wu, Yunsheng Ma, Lizhuang Zhang, Jiangning |
| contents | Existing industrial anomaly detection methods primarily concentrate on unsupervised learning with pristine RGB images. Yet, both RGB and 3D data are crucial for anomaly detection, and the datasets are seldom completely clean in practical scenarios. To address above challenges, this paper initially delves into the RGB-3D multi-modal noisy anomaly detection, proposing a novel noise-resistant M3DM-NR framework to leveraging strong multi-modal discriminative capabilities of CLIP. M3DM-NR consists of three stages: Stage-I introduces the Suspected References Selection module to filter a few normal samples from the training dataset, using the multimodal features extracted by the Initial Feature Extraction, and a Suspected Anomaly Map Computation module to generate a suspected anomaly map to focus on abnormal regions as reference. Stage-II uses the suspected anomaly maps of the reference samples as reference, and inputs image, point cloud, and text information to achieve denoising of the training samples through intra-modal comparison and multi-scale aggregation operations. Finally, Stage-III proposes the Point Feature Alignment, Unsupervised Feature Fusion, Noise Discriminative Coreset Selection, and Decision Layer Fusion modules to learn the pattern of the training dataset, enabling anomaly detection and segmentation while filtering out noise. Extensive experiments show that M3DM-NR outperforms state-of-the-art methods in 3D-RGB multi-modal noisy anomaly detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_02263 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising Wang, Chengjie Zhu, Haokun Peng, Jinlong Wang, Yue Yi, Ran Wu, Yunsheng Ma, Lizhuang Zhang, Jiangning Computer Vision and Pattern Recognition Existing industrial anomaly detection methods primarily concentrate on unsupervised learning with pristine RGB images. Yet, both RGB and 3D data are crucial for anomaly detection, and the datasets are seldom completely clean in practical scenarios. To address above challenges, this paper initially delves into the RGB-3D multi-modal noisy anomaly detection, proposing a novel noise-resistant M3DM-NR framework to leveraging strong multi-modal discriminative capabilities of CLIP. M3DM-NR consists of three stages: Stage-I introduces the Suspected References Selection module to filter a few normal samples from the training dataset, using the multimodal features extracted by the Initial Feature Extraction, and a Suspected Anomaly Map Computation module to generate a suspected anomaly map to focus on abnormal regions as reference. Stage-II uses the suspected anomaly maps of the reference samples as reference, and inputs image, point cloud, and text information to achieve denoising of the training samples through intra-modal comparison and multi-scale aggregation operations. Finally, Stage-III proposes the Point Feature Alignment, Unsupervised Feature Fusion, Noise Discriminative Coreset Selection, and Decision Layer Fusion modules to learn the pattern of the training dataset, enabling anomaly detection and segmentation while filtering out noise. Extensive experiments show that M3DM-NR outperforms state-of-the-art methods in 3D-RGB multi-modal noisy anomaly detection. |
| title | M3DM-NR: RGB-3D Noisy-Resistant Industrial Anomaly Detection via Multimodal Denoising |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.02263 |