Personalized Image Aesthetic Assessment via Preference-rich Sample Mining and Cohort Merging
Zhichao Yang1†,
Tianjiao Gu1†,
Zhixianhe Zhang1,
Xiangfei Sheng1,
Pengfei Chen1,
Leida Li1,2*
1School of Artificial Intelligence,
2State Key Laboratory of EMIM, Xidian University
†Equal contribution *Corresponding author
News
-
[2026-10-03] ✨✨ The Code and Pre-trained Weights, are now publicly available.
-
[2026-08-28] 🎉🎉 Congratulations! Our paper has been accepted for an Oral Presentation at ACM MM 2026.
-
[2026-07-10] 🎉🎉 Our paper, "Personalized Image Aesthetic Assessment via Preference-rich Sample Mining and Cohort Merging", has been accepted to ACMMM 2026!
## Introduction
This release contains the PARA implementation of PRAC: the Generic Aesthetic Predictor (GIAA), PreferSelect, PreferMerge, data loaders, and experiment configurations. Run commands from the repository root.
## Quick Start
### 1. Create the environment
The following environment matches the released configuration. Install the PyTorch build that matches the CUDA runtime available to the target GPU; the example uses PyTorch 2.4.1 with CUDA 12.1.
```bash
conda create -n prac python=3.10 -y
conda activate prac
conda install pytorch==2.4.1 torchvision==0.19.1 pytorch-cuda=12.1 -c pytorch -c nvidia
pip install -r requirements.txt
```
### 2. Download the model and data
Download the [mPLUG-Owl3-7B-241101 base checkpoint](https://huggingface.co/mPLUG/mPLUG-Owl3-7B-241101) and place it at `models/mPLUG-Owl3-7B`, or set `model.model_path` in the YAML files to another compatible local path. Then you can download the pretrained adapter from [Baidu Netdisk](https://pan.baidu.com/s/1pK-BDCCJLWci0tawbfYrog?pwd=3rd3) (pwd=`3rd3`).
Obtain the PARA dataset from [this link](https://web.xidian.edu.cn/ldli/en/dataset.html) and extract the archive's directory to `data`. The loaders also need derived files. Generate them from the original annotations with:
```bash
python scripts/prepare_giaa_labels.py --source data/PARA --output data/PARA
```
The final data layout is:
```text
data/PARA/
├── README.md # original dataset README
├── imgs// # original images
├── annotation/ # original PARA annotations
├── para_giaa_train_discretized.csv # from annotation/PARA-GiaaTrain.csv
├── para_giaa_test_discretized.csv # from annotation/PARA-GiaaTest.csv
└── ... # other original PARA files
```
The personalized-data loaders read the original `annotation/PARA-Images.csv` directly. User prompts are kept in the repository at `data/user_info_para.json`; the label-generation script does not copy or modify either file.
### 3. Run the inference demo
After the base checkpoint and PARA images are available, the demo automatically scores the first image below `data/PARA/imgs`:
```bash
python demo_inference.py
```
To use a particular image, a trained adapter, or a generated rationale:
```bash
python demo_inference.py \
--image data/PARA/imgs// \
--adapter-path runs/para/giaa_adapter \
--explain
```
## Repository Structure
```text
.
├── configs/
│ ├── giaa_train_config/ GIAA training configuration
│ ├── giaa_eval_config/ GIAA evaluation and demo configuration
│ ├── preferselect_config/ CCM/PDM data and model configuration
│ └── prefermerge_config/ LoRA-pool, FIM, and merge configuration
├── data/ Dataset layout and download notes
├── data_loader/ GIAA and personalized PARA data loaders
├── modules/MplugOwl3ForGIAA.py mPLUG-Owl3 wrapper and LoRA utilities
├── demo_inference.py Single-image distribution and score demo
├── mplug3_train_giaaBackbone.py Train the generic aesthetic predictor
├── mplug3_eval_giaaBackbone.py Evaluate a GIAA adapter
├── preferSelect_CCM.py Compute collective controversy (CCM)
├── preferSelect_PDM_fast.py Compute cached personalized deviation (PDM)
├── preferSelect_weights_ablation.py
│ Combine CCM and PDM for all alpha values
├── preferSelect.py Export ranked preference-rich samples
├── preferMerge.py Train LoRA pool or run adapter merging
├── preferMerge_FIM_fixed.py Compute FIM preference similarities
├── preferMerge_choice_fast.py Select a relevance/diversity cohort
├── utils.py Shared losses, metrics, and configuration helpers
├── CITATION.cff Citation metadata
├── LICENSE MIT license for the PRAC source code
└── docs/ Project page and reproduction guide
```
## Re-Training
### 1. Generic Aesthetic Predictor
Edit [`configs/giaa_train_config/para.yaml`](configs/giaa_train_config/para.yaml) if the model, data, batch size, or output path differs from the defaults, then run:
```bash
python mplug3_train_giaaBackbone.py
```
The trainer writes LoRA checkpoints below `runs/para/giaa`. Evaluate a selected adapter with:
```bash
python mplug3_eval_giaaBackbone.py
```
### 2. Preference-rich Sample Mining (PreferSelect)
Run the commands below:
```bash
python preferSelect_CCM.py
python preferSelect_PDM_fast.py
python preferSelect_weights_ablation.py
python preferSelect.py
```
### 3. Aesthetically-resonant Cohort Merging (PreferMerge)
Run the commands below:
```bash
python preferMerge_FIM_fixed.py
python preferMerge_choice_fast.py --top-n 6 --beta 0.5
python preferMerge.py
```
## Citation
If this code or paper helps your research, please cite:
```bibtex
@inproceedings{yang2026personalized,
title={Personalized Image Aesthetic Assessment via Preference-rich Sample Mining and Cohort Merging},
author={Yang, Zhichao and Gu, Tianjiao and Zhang, Zhixianhe and Sheng, Xiangfei and Chen, Pengfei and Li, Leida},
booktitle={Proceedings of the 34th ACM International Conference on Multimedia},
year={2026}
}
```
Citation metadata is also available in [`CITATION.cff`](CITATION.cff).
## License
The PRAC source code is available under the [MIT License](LICENSE).
