IEEE Journal of Selected Topics in Signal Processing · 2023 · 149 citations · 60 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningFeature-level FusionImage Feature EngineeringImage FusionImage QualityImage Quality AssessmentRepresentation LearningFeature FusionFeature Representation LearningFeature-based RepresentationHierarchical Feature FusionImage Feature FusionLearned Feature RepresentationsPerceptual Quality AssessmentQuality Assessment
Image quality assessment (IQA) is very important for both end-users and service providers since a high-quality image can significantly improve the user's quality of experience (QoE) and also benefit lots of computer vision algorithms. Most existing blind image quality assessment (BIQA) models were developed for synthetically distorted images, however, they perform poorly on in-the-wild images, which are widely existed in various practical applications. In this article, we propose a novel BIQA model for in-the-wild images by addressing two critical problems in this field: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">how to learn better quality-aware feature representation</i> , and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">how to solve the problem of insufficient training samples in terms of their content and distortion diversity</i> . Considering that perceptual visual quality is affected by both low-level visual features (e.g. distortions) and high-level semantic information (e.g. content), we first propose a staircase structure to hierarchically integrate the features from intermediate layers into the final feature representation, which enables the model to make full use of visual information from low-level to high-level. Then an iterative mixed database training (IMDT) strategy is proposed to train the BIQA model on multiple databases simultaneously, so the model can benefit from the increase in both training samples and image content and distortion diversity and can learn a more general feature representation. Experimental results show that the proposed model outperforms other state-of-the-art BIQA models on six in-the-wild IQA databases by a large margin. Moreover, the proposed model shows an excellent performance in the cross-database evaluation experiments, which further demonstrates that the learned feature representation is robust to images with diverse distortions and content.
60
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Mark Sandler, Andrew Howard, Menglong Zhu et al. · 2018 · 25.4K citations
The Pascal Visual Object Classes (VOC) Challenge
Mark Everingham, Luc Van Gool, Christopher K. I. Williams et al. · International Journal of Computer Vision · 2009 · 19.5K citations · Full text
Aggregated Residual Transformations for Deep Neural Networks
Saining Xie, Ross Girshick, Piotr Dollár et al. · 2017 · 11.9K citations