Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910954110844928 |
|---|---|
| author | Xu, Xiaohao Cao, Yunkang Zhang, Huaxin Sang, Nong Huang, Xiaonan |
| author_facet | Xu, Xiaohao Cao, Yunkang Zhang, Huaxin Sang, Nong Huang, Xiaonan |
| contents | Anomaly detection is vital in various industrial scenarios, including the identification of unusual patterns in production lines and the detection of manufacturing defects for quality control. Existing techniques tend to be specialized in individual scenarios and lack generalization capacities. In this study, our objective is to develop a generic anomaly detection model that can be applied in multiple scenarios. To achieve this, we custom-build generic visual language foundation models that possess extensive knowledge and robust reasoning abilities as anomaly detectors and reasoners. Specifically, we introduce a multi-modal prompting strategy that incorporates domain knowledge from experts as conditions to guide the models. Our approach considers diverse prompt types, including task descriptions, class context, normality rules, and reference images. In addition, we unify the input representation of multi-modality into a 2D image format, enabling multi-modal anomaly detection and reasoning. Our preliminary studies demonstrate that combining visual and language prompts as conditions for customizing the models enhances anomaly detection performance. The customized models showcase the ability to detect anomalies across different data modalities such as images, point clouds, and videos. Qualitative case studies further highlight the anomaly detection and reasoning capabilities, particularly for multi-object scenes and temporal data. Our code is publicly available at https://github.com/Xiaohao-Xu/Customizable-VLM |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_11083 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning Xu, Xiaohao Cao, Yunkang Zhang, Huaxin Sang, Nong Huang, Xiaonan Computer Vision and Pattern Recognition Computation and Language Anomaly detection is vital in various industrial scenarios, including the identification of unusual patterns in production lines and the detection of manufacturing defects for quality control. Existing techniques tend to be specialized in individual scenarios and lack generalization capacities. In this study, our objective is to develop a generic anomaly detection model that can be applied in multiple scenarios. To achieve this, we custom-build generic visual language foundation models that possess extensive knowledge and robust reasoning abilities as anomaly detectors and reasoners. Specifically, we introduce a multi-modal prompting strategy that incorporates domain knowledge from experts as conditions to guide the models. Our approach considers diverse prompt types, including task descriptions, class context, normality rules, and reference images. In addition, we unify the input representation of multi-modality into a 2D image format, enabling multi-modal anomaly detection and reasoning. Our preliminary studies demonstrate that combining visual and language prompts as conditions for customizing the models enhances anomaly detection performance. The customized models showcase the ability to detect anomalies across different data modalities such as images, point clouds, and videos. Qualitative case studies further highlight the anomaly detection and reasoning capabilities, particularly for multi-object scenes and temporal data. Our code is publicly available at https://github.com/Xiaohao-Xu/Customizable-VLM |
| title | Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2403.11083 |