Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2508.18188 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912553260548096 |
|---|---|
| author | Chung, Neo Christopher Binda, Jakub |
| author_facet | Chung, Neo Christopher Binda, Jakub |
| contents | Deep learning has transformed computer vision (CV), achieving outstanding performance in classification, segmentation, and related tasks. Such AI-based CV systems are becoming prevalent, with applications spanning from medical imaging to surveillance. State of the art models such as convolutional neural networks (CNNs) and vision transformers (ViTs) are often regarded as ``black boxes,'' offering limited transparency into their decision-making processes. Despite a recent advancement in explainable AI (XAI), explainability remains underutilized in practical CV deployments. A primary obstacle is the absence of integrated software solutions that connect XAI techniques with robust knowledge management and monitoring frameworks. To close this gap, we have developed Obz AI, a comprehensive software ecosystem designed to facilitate state-of-the-art explainability and observability for vision AI systems. Obz AI provides a seamless integration pipeline, from a Python client library to a full-stack analytics dashboard. With Obz AI, a machine learning engineer can easily incorporate advanced XAI methodologies, extract and analyze features for outlier detection, and continuously monitor AI models in real time. By making the decision-making mechanisms of deep models interpretable, Obz AI promotes observability and responsible deployment of computer vision systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18188 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Explain and Monitor Deep Learning Models for Computer Vision using Obz AI Chung, Neo Christopher Binda, Jakub Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction Software Engineering Deep learning has transformed computer vision (CV), achieving outstanding performance in classification, segmentation, and related tasks. Such AI-based CV systems are becoming prevalent, with applications spanning from medical imaging to surveillance. State of the art models such as convolutional neural networks (CNNs) and vision transformers (ViTs) are often regarded as ``black boxes,'' offering limited transparency into their decision-making processes. Despite a recent advancement in explainable AI (XAI), explainability remains underutilized in practical CV deployments. A primary obstacle is the absence of integrated software solutions that connect XAI techniques with robust knowledge management and monitoring frameworks. To close this gap, we have developed Obz AI, a comprehensive software ecosystem designed to facilitate state-of-the-art explainability and observability for vision AI systems. Obz AI provides a seamless integration pipeline, from a Python client library to a full-stack analytics dashboard. With Obz AI, a machine learning engineer can easily incorporate advanced XAI methodologies, extract and analyze features for outlier detection, and continuously monitor AI models in real time. By making the decision-making mechanisms of deep models interpretable, Obz AI promotes observability and responsible deployment of computer vision systems. |
| title | Explain and Monitor Deep Learning Models for Computer Vision using Obz AI |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction Software Engineering |
| url | https://arxiv.org/abs/2508.18188 |