xAI-CV: An Overview of Explainable Artificial Intelligence in Computer Vision
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908555427184640 |
|---|---|
| author | Van Tu, Nguyen Long, Pham Nguyen Hai Viet, Vo Hoai |
| author_facet | Van Tu, Nguyen Long, Pham Nguyen Hai Viet, Vo Hoai |
| contents | Deep learning has become the de facto standard and dominant paradigm in image analysis tasks, achieving state-of-the-art performance. However, this approach often results in "black-box" models, whose decision-making processes are difficult to interpret, raising concerns about reliability in critical applications. To address this challenge and provide human a method to understand how AI model process and make decision, the field of xAI has emerged. This paper surveys four representative approaches in xAI for visual perception tasks: (i) Saliency Maps, (ii) Concept Bottleneck Models (CBM), (iii) Prototype-based methods, and (iv) Hybrid approaches. We analyze their underlying mechanisms, strengths and limitations, as well as evaluation metrics, thereby providing a comprehensive overview to guide future research and applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18913 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | xAI-CV: An Overview of Explainable Artificial Intelligence in Computer Vision Van Tu, Nguyen Long, Pham Nguyen Hai Viet, Vo Hoai Computer Vision and Pattern Recognition Deep learning has become the de facto standard and dominant paradigm in image analysis tasks, achieving state-of-the-art performance. However, this approach often results in "black-box" models, whose decision-making processes are difficult to interpret, raising concerns about reliability in critical applications. To address this challenge and provide human a method to understand how AI model process and make decision, the field of xAI has emerged. This paper surveys four representative approaches in xAI for visual perception tasks: (i) Saliency Maps, (ii) Concept Bottleneck Models (CBM), (iii) Prototype-based methods, and (iv) Hybrid approaches. We analyze their underlying mechanisms, strengths and limitations, as well as evaluation metrics, thereby providing a comprehensive overview to guide future research and applications. |
| title | xAI-CV: An Overview of Explainable Artificial Intelligence in Computer Vision |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.18913 |