Resilient Multimodal Industrial Surface Defect Detection with Uncertain Sensors Availability
By: Shuai Jiang , Yunfeng Ma , Jingyu Zhou and more
Potential Business Impact:
Finds factory flaws even with broken cameras.
Multimodal industrial surface defect detection (MISDD) aims to identify and locate defect in industrial products by fusing RGB and 3D modalities. This article focuses on modality-missing problems caused by uncertain sensors availability in MISDD. In this context, the fusion of multiple modalities encounters several troubles, including learning mode transformation and information vacancy. To this end, we first propose cross-modal prompt learning, which includes: i) the cross-modal consistency prompt serves the establishment of information consistency of dual visual modalities; ii) the modality-specific prompt is inserted to adapt different input patterns; iii) the missing-aware prompt is attached to compensate for the information vacancy caused by dynamic modalities-missing. In addition, we propose symmetric contrastive learning, which utilizes text modality as a bridge for fusion of dual vision modalities. Specifically, a paired antithetical text prompt is designed to generate binary text semantics, and triple-modal contrastive pre-training is offered to accomplish multimodal learning. Experiment results show that our proposed method achieves 73.83% I-AUROC and 93.05% P-AUROC with a total missing rate 0.7 for RGB and 3D modalities (exceeding state-of-the-art methods 3.84% and 5.58% respectively), and outperforms existing approaches to varying degrees under different missing types and rates. The source code will be available at https://github.com/SvyJ/MISDD-MM.
Similar Papers
Diffusion-Based Restoration for Multi-Modal 3D Object Detection in Adverse Weather
CV and Pattern Recognition
Helps self-driving cars see better in bad weather.
Towards Robust and Realible Multimodal Misinformation Recognition with Incomplete Modality
Multimedia
Finds fake news even if parts are missing.
Multi Modal Attention Networks with Uncertainty Quantification for Automated Concrete Bridge Deck Delamination Detection
CV and Pattern Recognition
Finds hidden cracks in bridges using two types of scans.