JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment
This addresses data efficiency and robustness issues for researchers and practitioners in image quality assessment, though it is incremental as it builds on existing NR-IQA methods with a novel augmentation approach.
The paper tackles the problem of overfitting in no-reference image quality assessment (NR-IQA) due to limited datasets by proposing JNDMix, a data augmentation method that injects imperceptible JND noise into images without altering labels, which significantly improves model performance and data efficiency, achieving state-of-the-art results on benchmarks like LIVEC and KonIQ-10k.
Despite substantial progress in no-reference image quality assessment (NR-IQA), previous training models often suffer from over-fitting due to the limited scale of used datasets, resulting in model performance bottlenecks. To tackle this challenge, we explore the potential of leveraging data augmentation to improve data efficiency and enhance model robustness. However, most existing data augmentation methods incur a serious issue, namely that it alters the image quality and leads to training images mismatching with their original labels. Additionally, although only a few data augmentation methods are available for NR-IQA task, their ability to enrich dataset diversity is still insufficient. To address these issues, we propose a effective and general data augmentation based on just noticeable difference (JND) noise mixing for NR-IQA task, named JNDMix. In detail, we randomly inject the JND noise, imperceptible to the human visual system (HVS), into the training image without any adjustment to its label. Extensive experiments demonstrate that JNDMix significantly improves the performance and data efficiency of various state-of-the-art NR-IQA models and the commonly used baseline models, as well as the generalization ability. More importantly, JNDMix facilitates MANIQA to achieve the state-of-the-art performance on LIVEC and KonIQ-10k.