Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network

We propose a deep bilinear model for blind image quality assessment (BIQA) that works for both synthetically and authentically distorted images. Our model constitutes two streams of deep convolutional neural networks (CNN), specializing in the two distortion scenarios separately. For synthetic distortions, we first pre-train a CNN to classify the distortion type and level of an input image, whose ground truth label is readily available at a large scale. For authentic distortions, we make use of a pretrain CNN (VGG-16) for the image classification task. The two feature sets are bilinearly pooled into one representation for a final quality prediction. We fine-tune the whole network on target databases using a variant of stochastic gradient descent. Extensive experimental results show that the proposed model achieves state-of-the-art performance on both synthetic and authentic IQA databases. Furthermore, we verify the generalizability of our method on the large-scale Waterloo Exploration Database, and demonstrate its competitiveness using the group maximum differentiation competition methodology.