XAI-Enhanced Semantic Segmentation Models for Visual Quality Inspection
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_ | 1866909076607205376 |
|---|---|
| author | Clement, Tobias Nguyen, Truong Thanh Hung Abdelaal, Mohamed Cao, Hung |
| author_facet | Clement, Tobias Nguyen, Truong Thanh Hung Abdelaal, Mohamed Cao, Hung |
| contents | Visual quality inspection systems, crucial in sectors like manufacturing and logistics, employ computer vision and machine learning for precise, rapid defect detection. However, their unexplained nature can hinder trust, error identification, and system improvement. This paper presents a framework to bolster visual quality inspection by using CAM-based explanations to refine semantic segmentation models. Our approach consists of 1) Model Training, 2) XAI-based Model Explanation, 3) XAI Evaluation, and 4) Annotation Augmentation for Model Enhancement, informed by explanations and expert insights. Evaluations show XAI-enhanced models surpass original DeepLabv3-ResNet101 models, especially in intricate object segmentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_09900 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | XAI-Enhanced Semantic Segmentation Models for Visual Quality Inspection Clement, Tobias Nguyen, Truong Thanh Hung Abdelaal, Mohamed Cao, Hung Computer Vision and Pattern Recognition Artificial Intelligence Visual quality inspection systems, crucial in sectors like manufacturing and logistics, employ computer vision and machine learning for precise, rapid defect detection. However, their unexplained nature can hinder trust, error identification, and system improvement. This paper presents a framework to bolster visual quality inspection by using CAM-based explanations to refine semantic segmentation models. Our approach consists of 1) Model Training, 2) XAI-based Model Explanation, 3) XAI Evaluation, and 4) Annotation Augmentation for Model Enhancement, informed by explanations and expert insights. Evaluations show XAI-enhanced models surpass original DeepLabv3-ResNet101 models, especially in intricate object segmentation. |
| title | XAI-Enhanced Semantic Segmentation Models for Visual Quality Inspection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2401.09900 |