---
license: mit
language:
- en
base_model:
- MAGAer13/mplug-owl2-llama2-7b
---

DeQA-Score-LoRA model weights LoRA fine-tuned on KonIQ, SPAQ, and KADID datasets. 

See [Homepage](https://depictqa.github.io/deqa-score/) and [Source Code](https://github.com/zhiyuanyou/DeQA-Score) for details.

## Non-reference IQA Results (PLCC / SRCC)

| Dataset      | Fine-tuning | KonIQ     | SPAQ     | KADID    | PIPAL    | LIVE-Wild | AGIQA    | TID2013  | CSIQ     |
|--------------|-----------|-----------|----------|----------|----------|-----------|----------|----------|----------|
| Q-Align (Baseline) | Fully | 0.945 / 0.938 | 0.933 / 0.931 | 0.935 / 0.934 | 0.409 / 0.420 | 0.887 / 0.883 | 0.788 / 0.733 | 0.829 / 0.808 | 0.876 / 0.845 |
| DeQA-Score (Ours) | LoRA | **0.956 / 0.944** | **0.939 / 0.935** | **0.953 / 0.951** | **0.481 / 0.481** | **0.903 / 0.890** | **0.806 / 0.754** | **0.851 / 0.821** | **0.900 / 0.860** |