Learning from Mixed Datasets: A Monotonic Image Quality Assessment Model

TL;DR

This paper introduces a novel monotonic neural network approach for image quality assessment that effectively combines multiple datasets with differing annotations, enhancing model generalization.

Contribution

It proposes a dataset-shared quality regressor with dataset-specific transformers to unify diverse IQA datasets without aligning annotations.

Findings

Improved generalization on mixed datasets

Effective handling of diverse annotation criteria

Code implementation available online

Abstract

Deep learning based image quality assessment (IQA) 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 nontrivial to combine different IQA datasets, as their quality evaluation criteria, score ranges, view conditions, as well as subjects are usually not shared during the image quality annotation. In this paper, instead of aligning the annotations, we propose a monotonic neural network for IQA model learning with different datasets combined. In particular, our model consists of a dataset-shared quality regressor and several dataset-specific quality transformers. The quality regressor aims to obtain the perceptual qualities of each dataset while each quality transformer maps the perceptual qualities to the corresponding dataset annotations with their monotonicity maintained. The experimental results verify the effectiveness of the proposed learning strategy and our code is available at https://github.com/fzp0424/MonotonicIQA.