# Cross-IQA: Unsupervised Learning for Image Quality Assessment

arXiv: https://arxiv.org/abs/2405.04311 · HTML: https://mlsanity.com/paper/2405.04311/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 7 May 2024.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Residual Attention Network for Image Classification](https://mlsanity.com/paper/1704.06904/) (2017)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2004.05508/) (2020)
- [P-CNN: Pose-based CNN Features for Action Recognition](https://mlsanity.com/paper/1506.03607/) (2015)

## Abstract (arXiv)

Automatic perception of image quality is a challenging problem that impacts billions of Internet and social media users daily. To advance research in this field, we propose a no-reference image quality assessment (NR-IQA) method termed Cross-IQA based on vision transformer(ViT) model. The proposed Cross-IQA method can learn image quality features from unlabeled image data. We construct the pretext task of synthesized image reconstruction to unsupervised extract the image quality information based ViT block. The pretrained encoder of Cross-IQA is used to fine-tune a linear regression model for score prediction. Experimental results show that Cross-IQA can achieve state-of-the-art performance in assessing the low-frequency degradation information (e.g., color change, blurring, etc.) of images compared with the classical full-reference IQA and NR-IQA under the same datasets.