Explaining Defect Detection with Saliency Maps
| Autor: | Djamila Aouada, Francois Fouquet, Assaad Moawad, Thomas Hartmann, Joe Lorentz |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Edge device
Computational complexity theory business.industry Computer science media_common.quotation_subject computer.software_genre Domain (software engineering) Metric (mathematics) Classifier (linguistics) Quality (business) Data mining business Throughput (business) Quality assurance computer media_common |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783030794620 IEA/AIE (2) |
| DOI: | 10.1007/978-3-030-79463-7_43 |
| Popis: | The rising quality and throughput demands of the manufacturing domain require flexible, accurate and explainable computer-vision solutions for defect detection. Deep Neural Networks (DNNs) reach state-of-the-art performance on various computer-vision tasks but wide-spread application in the industrial domain is blocked by the lacking explainability of DNN decisions. A promising, human-readable solution is given by saliency maps, heatmaps highlighting the image areas that influence the classifier’s decision. This work evaluates a selection of saliency methods in the area of industrial quality assurance. To this end we propose the distance pointing game, a new metric to quantify the meaningfulness of saliency maps for defect detection. We provide steps to prepare a publicly available dataset on defective steel plates for the proposed metric. Additionally, the computational complexity is investigated to determine which methods could be integrated on industrial edge devices. Our results show that DeepLift, GradCAM and GradCAM++ outperform the alternatives while the computational cost is feasible for real time applications even on edge devices. This indicates that the respective methods could be used as an additional, autonomous post-classification step to explain decisions taken by intelligent quality assurance systems. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|