MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment

TL;DR

This paper introduces MetaIQA, a deep meta-learning approach for no-reference image quality assessment that learns shared quality evaluation knowledge across various distortions, enabling quick adaptation to new distortion types and outperforming existing methods.

Contribution

The paper proposes a novel deep meta-learning framework for NR-IQA that effectively captures shared quality assessment knowledge and adapts rapidly to new distortions, addressing generalization issues.

Findings

MetaIQA outperforms state-of-the-art IQA metrics in experiments.

Meta-model generalizes well from synthetic to authentic distortions.

The approach enables quick adaptation to new distortion types.

Abstract

Recently, increasing interest has been drawn in exploiting deep convolutional neural networks (DCNNs) for no-reference image quality assessment (NR-IQA). Despite of the notable success achieved, there is a broad consensus that training DCNNs heavily relies on massive annotated data. Unfortunately, IQA is a typical small sample problem. Therefore, most of the existing DCNN-based IQA metrics operate based on pre-trained networks. However, these pre-trained networks are not designed for IQA task, leading to generalization problem when evaluating different types of distortions. With this motivation, this paper presents a no-reference IQA metric based on deep meta-learning. The underlying idea is to learn the meta-knowledge shared by human when evaluating the quality of images with various distortions, which can then be adapted to unknown distortions easily. Specifically, we first collect a number of NR-IQA tasks for different distortions. Then meta-learning is adopted to learn the prior knowledge shared by diversified distortions. Finally, the quality prior model is fine-tuned on a target NR-IQA task for quickly obtaining the quality model. Extensive experiments demonstrate that the proposed metric outperforms the state-of-the-arts by a large margin. Furthermore, the meta-model learned from synthetic distortions can also be easily generalized to authentic distortions, which is highly desired in real-world applications of IQA metrics.