{"ID":2867100,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.18913","arxiv_id":"2509.18913","title":"xAI-CV: An Overview of Explainable Artificial Intelligence in Computer Vision","abstract":"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.","short_abstract":"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 ad...","url_abs":"https://arxiv.org/abs/2509.18913","url_pdf":"https://arxiv.org/pdf/2509.18913v1","authors":"[\"Nguyen Van Tu\",\"Pham Nguyen Hai Long\",\"Vo Hoai Viet\"]","published":"2025-09-23T12:33:54Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}