PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Zewen, Qin, Haina, Wang, Juan, Yuan, Chunfeng, Li, Bing, Hu, Weiming, Wang, Liang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914707970981888
author Chen, Zewen
Qin, Haina
Wang, Juan
Yuan, Chunfeng
Li, Bing
Hu, Weiming
Wang, Liang
author_facet Chen, Zewen
Qin, Haina
Wang, Juan
Yuan, Chunfeng
Li, Bing
Hu, Weiming
Wang, Liang
contents Due to the diversity of assessment requirements in various application scenarios for the IQA task, existing IQA methods struggle to directly adapt to these varied requirements after training. Thus, when facing new requirements, a typical approach is fine-tuning these models on datasets specifically created for those requirements. However, it is time-consuming to establish IQA datasets. In this work, we propose a Prompt-based IQA (PromptIQA) that can directly adapt to new requirements without fine-tuning after training. On one hand, it utilizes a short sequence of Image-Score Pairs (ISP) as prompts for targeted predictions, which significantly reduces the dependency on the data requirements. On the other hand, PromptIQA is trained on a mixed dataset with two proposed data augmentation strategies to learn diverse requirements, thus enabling it to effectively adapt to new requirements. Experiments indicate that the PromptIQA outperforms SOTA methods with higher performance and better generalization. The code will be available.
format Preprint
id arxiv_https___arxiv_org_abs_2403_04993
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts
Chen, Zewen
Qin, Haina
Wang, Juan
Yuan, Chunfeng
Li, Bing
Hu, Weiming
Wang, Liang
Computer Vision and Pattern Recognition
Due to the diversity of assessment requirements in various application scenarios for the IQA task, existing IQA methods struggle to directly adapt to these varied requirements after training. Thus, when facing new requirements, a typical approach is fine-tuning these models on datasets specifically created for those requirements. However, it is time-consuming to establish IQA datasets. In this work, we propose a Prompt-based IQA (PromptIQA) that can directly adapt to new requirements without fine-tuning after training. On one hand, it utilizes a short sequence of Image-Score Pairs (ISP) as prompts for targeted predictions, which significantly reduces the dependency on the data requirements. On the other hand, PromptIQA is trained on a mixed dataset with two proposed data augmentation strategies to learn diverse requirements, thus enabling it to effectively adapt to new requirements. Experiments indicate that the PromptIQA outperforms SOTA methods with higher performance and better generalization. The code will be available.
title PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.04993