# ExIQA: Explainable Image Quality Assessment Using Distortion Attributes

arXiv: https://arxiv.org/abs/2409.06853 · HTML: https://mlsanity.com/paper/2409.06853/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 55 references that are in the map.
- First posted on arXiv 10 Sep 2024.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild](https://mlsanity.com/paper/2304.00451/) (2023)
- [Image Quality Assessment using Contrastive Learning](https://mlsanity.com/paper/2110.13266/) (2021)
- [ARNIQA: Learning Distortion Manifold for Image Quality Assessment](https://mlsanity.com/paper/2310.14918/) (2023)
- [Towards Explainable Deep Neural Networks (xDNN)](https://mlsanity.com/paper/1912.02523/) (2019)
- [On the Use of Deep Learning for Blind Image Quality Assessment](https://mlsanity.com/paper/1602.05531/) (2016)
- [GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through Prompts](https://mlsanity.com/paper/2305.12477/) (2023)
- [DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning](https://mlsanity.com/paper/2001.08113/) (2020)
- [Doubly Right Object Recognition: A Why Prompt for Visual Rationales](https://mlsanity.com/paper/2212.06202/) (2022)
- [A deep Convolutional Neural Network for topology optimization with strong generalization ability](https://mlsanity.com/paper/1901.07761/) (2019)
- [Rectify ViT Shortcut Learning by Visual Saliency](https://mlsanity.com/paper/2206.08567/) (2022)
- [ECOR: Explainable CLIP for Object Recognition](https://mlsanity.com/paper/2404.12839/) (2024)
- [Towards a Video Quality Assessment based Framework for Enhancement of Laparoscopic Videos](https://mlsanity.com/paper/2003.12679/) (2020)
- [Residual Networks based Distortion Classification and Ranking for Laparoscopic Image Quality Assessment](https://mlsanity.com/paper/2106.06784/) (2021)
- [A Neural Network based Framework for Effective Laparoscopic Video Quality Assessment](https://mlsanity.com/paper/2202.04517/) (2022)
- [Collaborative Auto-encoding for Blind Image Quality Assessment](https://mlsanity.com/paper/2305.14684/) (2023)

## Abstract (arXiv)

Blind Image Quality Assessment (BIQA) aims to develop methods that estimate the quality scores of images in the absence of a reference image. In this paper, we approach BIQA from a distortion identification perspective, where our primary goal is to predict distortion types and strengths using Vision-Language Models (VLMs), such as CLIP, due to their extensive knowledge and generalizability. Based on these predicted distortions, we then estimate the quality score of the image. To achieve this, we propose an explainable approach for distortion identification based on attribute learning. Instead of prompting VLMs with the names of distortions, we prompt them with the attributes or effects of distortions and aggregate this information to infer the distortion strength. Additionally, we consider multiple distortions per image, making our method more scalable. To support this, we generate a dataset consisting of 100,000 images for efficient training. Finally, attribute probabilities are retrieved and fed into a regressor to predict the image quality score. The results show that our approach, besides its explainability and transparency, achieves state-of-the-art (SOTA) performance across multiple datasets in both PLCC and SRCC metrics. Moreover, the zero-shot results demonstrate the generalizability of the proposed approach.