Learning from mixed datasets: A monotonic image quality assessment model

• Published in: Electronics letters Vol. 59; no. 3
• Main Authors: Feng, Zhaopeng, Zhang, Keyang, Jia, Shuyue, Chen, Baoliang, Wang, Shiqi
• Format: Journal Article
• Language: English
• Published: Stevenage John Wiley & Sons, Inc 01.02.2023; Wiley
• Subjects: Annotations; Datasets; Deep learning; Effectiveness; image and vision processing and display technology; Image enhancement; image processing; Image quality; Neural networks; Quality assessment; Transformers

Deep learning based image quality assessment models usually learn to predict image quality from a single dataset, leading the model to overfit specific scenes. To account for this, mixed datasets training can be an effective way to enhance the generalization capability of the model. However, it is n...