# Adaptive Mixed-Scale Feature Fusion Network for Blind AI-Generated Image Quality Assessment

arXiv: https://arxiv.org/abs/2404.15163 · HTML: https://mlsanity.com/paper/2404.15163/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 73 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale](https://mlsanity.com/paper/2303.06555/) (2023)
- [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://mlsanity.com/paper/2108.06858/) (2021)
- [AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2306.04717/) (2023)
- [LAFITE: Towards Language-Free Training for Text-to-Image Generation](https://mlsanity.com/paper/2111.13792/) (2021)
- [Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild](https://mlsanity.com/paper/2304.00451/) (2023)
- [LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation](https://mlsanity.com/paper/2305.11116/) (2023)
- [CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not](https://mlsanity.com/paper/2303.13440/) (2023)
- [Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Training](https://mlsanity.com/paper/2105.14550/) (2021)
- [AIGCIQA2023: A Large-scale Image Quality Assessment Database for AI Generated Images: from the Perspectives of Quality, Authenticity and Correspondence](https://mlsanity.com/paper/2307.00211/) (2023)
- [Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2](https://mlsanity.com/paper/2210.00586/) (2022)
- [A Perceptual Quality Assessment Exploration for AIGC Images](https://mlsanity.com/paper/2303.12618/) (2023)
- [Adversarial Text-to-Image Synthesis: A Review](https://mlsanity.com/paper/2101.09983/) (2021)
- [CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification](https://mlsanity.com/paper/2307.16634/) (2023)

## Built on by (most cited first, 10 of 10)

- [AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM](https://mlsanity.com/paper/2411.17221/) (2024)
- [Quality Assessment for AI Generated Images with Instruction Tuning](https://mlsanity.com/paper/2405.07346/) (2024)
- [CLIPVQA:Video Quality Assessment via CLIP](https://mlsanity.com/paper/2407.04928/) (2024)
- [Perceptual Visual Quality Assessment: Principles, Methods, and Future Directions](https://mlsanity.com/paper/2503.00625/) (2025)
- [Decoupling Semantics from Distortions: Multi-Scale Two-Stream Vision-Language Alignment for AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2606.16799/) (2026)
- [M3-AGIQA: Multimodal, Multi-Round, Multi-Aspect AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2502.15167/) (2025)
- [Secure Video Quality Assessment Resisting Adversarial Attacks](https://mlsanity.com/paper/2410.06866/) (2024)
- [HyperAlign: Hyperbolic Entailment Cones for Adaptive Text-to-Image Alignment Assessment](https://mlsanity.com/paper/2601.04614/) (2026)
- [Hierarchical Fusion and Joint Aggregation: A Multi-Level Feature Representation Method for AIGC Image Quality Assessment](https://mlsanity.com/paper/2507.17182/) (2025)
- [Patch Knowledge Transfer for Efficient AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2607.05605/) (2026)

## Abstract (arXiv)

With the increasing maturity of the text-to-image and image-to-image generative models, AI-generated images (AGIs) have shown great application potential in advertisement, entertainment, education, social media, etc. Although remarkable advancements have been achieved in generative models, very few efforts have been paid to design relevant quality assessment models. In this paper, we propose a novel blind image quality assessment (IQA) network, named AMFF-Net, for AGIs. AMFF-Net evaluates AGI quality from three dimensions, i.e., "visual quality", "authenticity", and "consistency". Specifically, inspired by the characteristics of the human visual system and motivated by the observation that "visual quality" and "authenticity" are characterized by both local and global aspects, AMFF-Net scales the image up and down and takes the scaled images and original-sized image as the inputs to obtain multi-scale features. After that, an Adaptive Feature Fusion (AFF) block is used to adaptively fuse the multi-scale features with learnable weights. In addition, considering the correlation between the image and prompt, AMFF-Net compares the semantic features from text encoder and image encoder to evaluate the text-to-image alignment. We carry out extensive experiments on three AGI quality assessment databases, and the experimental results show that our AMFF-Net obtains better performance than nine state-of-the-art blind IQA methods. The results of ablation experiments further demonstrate the effectiveness of the proposed multi-scale input strategy and AFF block.