# Parameter-Efficient Adaptation of mPLUG-Owl2 via Pixel-Level Visual Prompts for NR-IQA

arXiv: https://arxiv.org/abs/2509.03494 · HTML: https://mlsanity.com/paper/2509.03494/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 34 references that are in the map.
- First posted on arXiv 3 Sep 2025.

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [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)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration](https://mlsanity.com/paper/2311.04257/) (2023)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [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)
- [Exploring Visual Prompts for Adapting Large-Scale Models](https://mlsanity.com/paper/2203.17274/) (2022)
- [Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision](https://mlsanity.com/paper/2309.14181/) (2023)
- [From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality](https://mlsanity.com/paper/1912.10088/) (2019)
- [Massive Online Crowdsourced Study of Subjective and Objective Picture Quality](https://mlsanity.com/paper/1511.02919/) (2015)
- [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://mlsanity.com/paper/2108.06858/) (2021)
- [Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models](https://mlsanity.com/paper/2311.06783/) (2023)
- [AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2306.04717/) (2023)
- [Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild](https://mlsanity.com/paper/2005.13983/) (2020)
- [Image Quality Assessment using Contrastive Learning](https://mlsanity.com/paper/2110.13266/) (2021)
- [Understanding and Improving Visual Prompting: A Label-Mapping Perspective](https://mlsanity.com/paper/2211.11635/) (2022)
- [A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment](https://mlsanity.com/paper/2403.10854/) (2024)
- [A Survey of Automatic Prompt Engineering: An Optimization Perspective](https://mlsanity.com/paper/2502.11560/) (2025)
- [Unleashing the Power of Visual Prompting At the Pixel Level](https://mlsanity.com/paper/2212.10556/) (2022)
- [AutoVP: An Automated Visual Prompting Framework and Benchmark](https://mlsanity.com/paper/2310.08381/) (2023)
- [Q-Adapt: Adapting LMM for Visual Quality Assessment with Progressive Instruction Tuning](https://mlsanity.com/paper/2504.01655/) (2025)
- [Robust Adaptation of Foundation Models with Black-Box Visual Prompting](https://mlsanity.com/paper/2407.17491/) (2024)
- [Multi-Modal Prompt Learning on Blind Image Quality Assessment](https://mlsanity.com/paper/2404.14949/) (2024)

## Abstract (arXiv)

In this paper, we propose a novel parameter-efficient adaptation method for No- Reference Image Quality Assessment (NR-IQA) using visual prompts optimized in pixel-space. Unlike full fine-tuning of Multimodal Large Language Models (MLLMs), our approach trains only 600K parameters at most (< 0.01% of the base model), while keeping the underlying model fully frozen. During inference, these visual prompts are combined with images via addition and processed by mPLUG-Owl2 with the textual query "Rate the technical quality of the image." Evaluations across distortion types (synthetic, realistic, AI-generated) on KADID- 10k, KonIQ-10k, and AGIQA-3k demonstrate competitive performance against full finetuned methods and specialized NR-IQA models, achieving 0.93 SRCC on KADID-10k. To our knowledge, this is the first work to leverage pixel-space visual prompts for NR-IQA, enabling efficient MLLM adaptation for low-level vision tasks. The source code is publicly available at https: // github. com/ yahya-ben/ mplug2-vp-for-nriqa.