Image Quality Assessment using Contrastive Learning

Abstract

We consider the problem of obtaining image quality representations in a self-supervised manner. We use prediction of distortion type and degree as an auxiliary task to learn features from an unlabeled image dataset containing a mixture of synthetic and realistic distortions. We then train a deep Convolutional Neural Network (CNN) using a contrastive pairwise objective to solve the auxiliary problem. We refer to the proposed training framework and resulting deep IQA model as the CONTRastive Image QUality Evaluator (CONTRIQUE). During evaluation, the CNN weights are frozen and a linear regressor maps the learned representations to quality scores in a No-Reference (NR) setting. We show through extensive experiments that CONTRIQUE achieves competitive performance when compared to state-of-the-art NR image quality models, even without any additional fine-tuning of the CNN backbone. The learned representations are highly robust and generalize well across images afflicted by either synthetic or authentic distortions. Our results suggest that powerful quality representations with perceptual relevance can be obtained without requiring large labeled subjective image quality datasets. The implementations used in this paper are available at \url{https://github.com/pavancm/CONTRIQUE}.

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Simple Framework for Contrastive Learning of Visual Representations
• Image Quality Assessment: Unifying Structure and Texture Similarity
• Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
• Learning Representations by Maximizing Mutual Information Across Views
• Comparison of Image Quality Models for Optimization of Image Processing Systems
• RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content
• Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
• A Probabilistic Quality Representation Approach to Deep Blind Image Quality Prediction
• ST-GREED: Space-Time Generalized Entropic Differences for Frame Rate Dependent Video Quality Prediction
• DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning

Cited by in corpus (6)

• RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training
• Advances in Artificial Intelligence: A Review for the Creative Industries
• BVI-VFI: A Video Quality Database for Video Frame Interpolation
• Subjective and Objective Quality Assessment of Rendered Human Avatar Videos in Virtual Reality
• RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content
• Sea-Undistort: A Dataset for Through-Water Image Restoration in High Resolution Airborne Bathymetric Mapping