---
title: "Deep Opinion-Unaware Blind Image Quality Assessment by Learning and Adapting from Multiple Annotators"
authors:
  - "Zhihua Wang"
  - "Xuelin Liu"
  - "Jiebin Yan"
  - "Jie Wen"
  - "Wei Wang"
  - "Chao Huang"
doi: "10.24963/ijcai.2025/227"
url: "https://ijcai.org/proceedings/2025/227"
pdf: "https://ijcai.org/proceedings/2025/0227.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "2036-2044"
track: "Main Track"
keywords:
  - "Computer Vision: CV: Computational photography"
  - "Computer Vision: CV: Low-level Vision"
---

# Deep Opinion-Unaware Blind Image Quality Assessment by Learning and Adapting from Multiple Annotators

Zhihua Wang, Xuelin Liu, Jiebin Yan, Jie Wen, Wei Wang, Chao Huang

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 2036-2044. DOI: [10.24963/ijcai.2025/227](https://doi.org/10.24963/ijcai.2025/227)

## Abstract

Existing deep neural network (DNN)-based blind image quality assessment (BIQA) methods primarily rely on human-rated datasets for training. However, collecting human labels is extremely time-consuming and labor-intensive, posing a significant bottleneck for practical applications. To address this challenge, we propose a Deep opinion-Unaware BIQA model by learning and adapting from Multiple Annotators, termed DUBMA,  thereby eliminating the need for human annotations. Specifically, we first generate a large-scale set of distorted image pairs and then assign relative quality rankings using existing full-reference IQA models. The resulting dataset is subsequently employed for training our DUBMA.
Due to the inherent discrepancies between synthetic and real-world distortions, a domain shift may occur. To address this, we propose an outlier-robust unsupervised domain adaptation approach leveraging optimal transport. This strategy effectively reduces the gap between synthetic and real-world distortion domains, thereby boosting the model’s adaptability and overall performance. Extensive experiments show that DUBMA outperforms existing opinion-unaware BIQA methods in terms of prediction accuracy across multiple datasets.