# Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment

arXiv: https://arxiv.org/abs/2003.03849 · HTML: https://mlsanity.com/paper/2003.03849/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2020.

## Built on by (most cited first, 24 of 24)

- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank](https://mlsanity.com/paper/2505.14460/) (2025)
- [Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models](https://mlsanity.com/paper/2307.13981/) (2023)
- [Continual Learning for Blind Image Quality Assessment](https://mlsanity.com/paper/2102.09717/) (2021)
- [Q-Ground: Image Quality Grounding with Large Multi-modality Models](https://mlsanity.com/paper/2407.17035/) (2024)
- [Troubleshooting Blind Image Quality Models in the Wild](https://mlsanity.com/paper/2105.06747/) (2021)
- [PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts](https://mlsanity.com/paper/2403.04993/) (2024)
- [SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning](https://mlsanity.com/paper/2411.10161/) (2024)
- [G-Refine: A General Quality Refiner for Text-to-Image Generation](https://mlsanity.com/paper/2404.18343/) (2024)
- [Semi-Supervised Deep Ensembles for Blind Image Quality Assessment](https://mlsanity.com/paper/2106.14008/) (2021)
- [Image Quality Assessment: Integrating Model-Centric and Data-Centric Approaches](https://mlsanity.com/paper/2207.14769/) (2022)
- [AI-Generated Image Quality Assessment Based on Task-Specific Prompt and Multi-Granularity Similarity](https://mlsanity.com/paper/2411.16087/) (2024)
- [Max360IQ: Blind Omnidirectional Image Quality Assessment with Multi-axis Attention](https://mlsanity.com/paper/2502.19046/) (2025)
- [Learning Transformer Features for Image Quality Assessment](https://mlsanity.com/paper/2112.00485/) (2021)
- [Blind Image Quality Assessment: A Brief Survey](https://mlsanity.com/paper/2312.16551/) (2023)
- [Pairwise Comparisons Are All You Need](https://mlsanity.com/paper/2403.09746/) (2024)
- [Computational Analysis of Degradation Modeling in Blind Panoramic Image Quality Assessment](https://mlsanity.com/paper/2503.03255/) (2025)
- [SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack against No-Reference Image Quality Assessment Models](https://mlsanity.com/paper/2509.18546/) (2025)
- [MDS-VQA: Model-Informed Data Selection for Video Quality Assessment](https://mlsanity.com/paper/2603.11525/) (2026)
- [LIME-Eval: Rethinking Low-light Image Enhancement Evaluation via Object Detection](https://mlsanity.com/paper/2410.08810/) (2024)
- [ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking](https://mlsanity.com/paper/2603.20785/) (2026)
- [Causal Disentanglement-Inspired Degradation Representation Learning for Full-Reference Image Quality Assessment](https://mlsanity.com/paper/2604.21654/) (2026)
- [Blind Stereoscopic Omnidirectional Image Quality Assessment Using Predictive Coding Hierarchy](https://mlsanity.com/paper/2608.28798/) (2026)
- [Di2CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schr"odinger Bridge Transformer](https://mlsanity.com/paper/2608.29043/) (2026)

## Abstract (arXiv)

The research in image quality assessment (IQA) has a long history, and significant progress has been made by leveraging recent advances in deep neural networks (DNNs). Despite high correlation numbers on existing IQA datasets, DNN-based models may be easily falsified in the group maximum differentiation (gMAD) competition with strong counterexamples being identified. Here we show that gMAD examples can be used to improve blind IQA (BIQA) methods. Specifically, we first pre-train a DNN-based BIQA model using multiple noisy annotators, and fine-tune it on multiple subject-rated databases of synthetically distorted images, resulting in a top-performing baseline model. We then seek pairs of images by comparing the baseline model with a set of full-reference IQA methods in gMAD. The resulting gMAD examples are most likely to reveal the relative weaknesses of the baseline, and suggest potential ways for refinement. We query ground truth quality annotations for the selected images in a well controlled laboratory environment, and further fine-tune the baseline on the combination of human-rated images from gMAD and existing databases. This process may be iterated, enabling active and progressive fine-tuning from gMAD examples for BIQA. We demonstrate the feasibility of our active learning scheme on a large-scale unlabeled image set, and show that the fine-tuned method achieves improved generalizability in gMAD, without destroying performance on previously trained databases.