DSMix: Distortion-Induced Sensitivity Map Based Pre-training for No-Reference Image Quality Assessment
This addresses a data scarcity problem for researchers and practitioners in computer vision, but it is incremental as it builds on existing deep learning-based IQA methods.
The paper tackles the lack of labeled data in image quality assessment (IQA) by introducing DSMix, a data augmentation technique that uses distortion-induced sensitivity maps to pre-train models, achieving significant predictive and generalization performance on synthetic and authentic datasets without full model fine-tuning.
Image quality assessment (IQA) has long been a fundamental challenge in image understanding. In recent years, deep learning-based IQA methods have shown promising performance. However, the lack of large amounts of labeled data in the IQA field has hindered further advancements in these methods. This paper introduces DSMix, a novel data augmentation technique specifically designed for IQA tasks, aiming to overcome this limitation. DSMix leverages the distortion-induced sensitivity map (DSM) of an image as prior knowledge. It applies cut and mix operations to diverse categories of synthetic distorted images, assigning confidence scores to class labels based on the aforementioned prior knowledge. In the pre-training phase using DSMix-augmented data, knowledge distillation is employed to enhance the model's ability to extract semantic features. Experimental results on both synthetic and authentic IQA datasets demonstrate the significant predictive and generalization performance achieved by DSMix, without requiring fine-tuning of the full model. Code is available at \url{https://github.com/I2-Multimedia-Lab/DSMix}.