![[2507.19418] DEFNet: Multitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessment](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2507.19418] DEFNet: Multitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessment
Summary
The paper introduces DEFNet, a multitask-based deep evidential fusion network designed to enhance blind image quality assessment (BIQA) by integrating auxiliary tasks and advanced uncertainty estimation techniques.
Why It Matters
This research addresses the limitations of existing BIQA methods by proposing a robust framework that improves performance through multitask optimization and effective uncertainty estimation. As image quality assessment is crucial in various applications, advancements in this area can lead to better visual experiences and more reliable image processing technologies.
Key Takeaways
- DEFNet enhances blind image quality assessment through multitask optimization.
- A novel trustworthy information fusion strategy improves feature integration.
- The framework employs advanced uncertainty estimation techniques for better reliability.
- Extensive experiments validate DEFNet's effectiveness on various datasets.
- The model shows strong generalization capabilities for unseen scenarios.
Computer Science > Computer Vision and Pattern Recognition arXiv:2507.19418 (cs) [Submitted on 25 Jul 2025] Title:DEFNet: Multitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessment Authors:Yiwei Lou, Yuanpeng He, Rongchao Zhang, Yongzhi Cao, Hanpin Wang, Yu Huang View a PDF of the paper titled DEFNet: Multitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessment, by Yiwei Lou and 5 other authors View PDF HTML (experimental) Abstract:Blind image quality assessment (BIQA) methods often incorporate auxiliary tasks to improve performance. However, existing approaches face limitations due to insufficient integration and a lack of flexible uncertainty estimation, leading to suboptimal performance. To address these challenges, we propose a multitasks-based Deep Evidential Fusion Network (DEFNet) for BIQA, which performs multitask optimization with the assistance of scene and distortion type classification tasks. To achieve a more robust and reliable representation, we design a novel trustworthy information fusion strategy. It first combines diverse features and patterns across sub-regions to enhance information richness, and then performs local-global information fusion by balancing fine-grained details with coarse-grained context. Moreover, DEFNet exploits advanced uncertainty estimation technique inspired by evidential learning with the help of normal-inverse gamma distribution mixture. Extensive experiments on both synthetic and aut...