GMC-IQA: Exploiting Global-correlation and Mean-opinion Consistency for No-reference Image Quality Assessment

• URL: http://arxiv.org/abs/2401.10511v1
• Date: Fri, 19 Jan 2024 06:03:01 GMT
• Title: GMC-IQA: Exploiting Global-correlation and Mean-opinion Consistency for No-reference Image Quality Assessment
• Authors: Zewen Chen, Juan Wang, Bing Li, Chunfeng Yuan, Weiming Hu, Junxian Liu, Peng Li, Yan Wang, Youqun Zhang, Congxuan Zhang
• Abstract summary: We construct a novel loss function and network to exploit Global-correlation and Mean-opinion Consistency. We propose a novel GCC loss by defining a pairwise preference-based rank estimation to solve the non-differentiable problem of SROCC. We also propose a mean-opinion network, which integrates diverse opinion features to alleviate the randomness of weight learning.
• Score: 40.33163764161929
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Due to the subjective nature of image quality assessment (IQA), assessing which image has better quality among a sequence of images is more reliable than assigning an absolute mean opinion score for an image. Thus, IQA models are evaluated by global correlation consistency (GCC) metrics like PLCC and SROCC, rather than mean opinion consistency (MOC) metrics like MAE and MSE. However, most existing methods adopt MOC metrics to define their loss functions, due to the infeasible computation of GCC metrics during training. In this work, we construct a novel loss function and network to exploit Global-correlation and Mean-opinion Consistency, forming a GMC-IQA framework. Specifically, we propose a novel GCC loss by defining a pairwise preference-based rank estimation to solve the non-differentiable problem of SROCC and introducing a queue mechanism to reserve previous data to approximate the global results of the whole data. Moreover, we propose a mean-opinion network, which integrates diverse opinion features to alleviate the randomness of weight learning and enhance the model robustness. Experiments indicate that our method outperforms SOTA methods on multiple authentic datasets with higher accuracy and generalization. We also adapt the proposed loss to various networks, which brings better performance and more stable training.

Related papers

• Descriptive Image Quality Assessment in the Wild [25.503311093471076]
  VLM-based Image Quality Assessment (IQA) seeks to describe image quality linguistically to align with human expression. We introduce Depicted image Quality Assessment in the Wild (DepictQA-Wild) Our method includes a multi-functional IQA task paradigm that encompasses both assessment and comparison tasks, brief and detailed responses, full-reference and non-reference scenarios.
  arXiv  Detail & Related papers  (2024-05-29T07:49:15Z)
• Global-Local Image Perceptual Score (GLIPS): Evaluating Photorealistic Quality of AI-Generated Images [0.7499722271664147]
  The Global-Local Image Perceptual Score (GLIPS) is an image metric designed to assess the photorealistic image quality of AI-generated images. Comprehensive tests across various generative models demonstrate that GLIPS consistently outperforms existing metrics like FID, SSIM, and MS-SSIM in terms of correlation with human scores.
  arXiv  Detail & Related papers  (2024-05-15T15:19:23Z)
• Multi-Modal Prompt Learning on Blind Image Quality Assessment [65.0676908930946]
  Image Quality Assessment (IQA) models benefit significantly from semantic information, which allows them to treat different types of objects distinctly. Traditional methods, hindered by a lack of sufficiently annotated data, have employed the CLIP image-text pretraining model as their backbone to gain semantic awareness. Recent approaches have attempted to address this mismatch using prompt technology, but these solutions have shortcomings. This paper introduces an innovative multi-modal prompt-based methodology for IQA.
  arXiv  Detail & Related papers  (2024-04-23T11:45:32Z)
• Beyond Score Changes: Adversarial Attack on No-Reference Image Quality Assessment from Two Perspectives [15.575900555433863]
  We introduce a new framework of correlation-error-based attacks that perturb both the correlation within an image set and score changes on individual images. Our research focuses on ranking-related correlation metrics like Spearman's Rank-Order Correlation Coefficient (SROCC) and prediction error-related metrics like Mean Squared Error (MSE)
  arXiv  Detail & Related papers  (2024-04-20T05:24:06Z)
• GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models [60.48306899271866]
  We present a new framework, called GREAT Score, for global robustness evaluation of adversarial perturbation using generative models. We show high correlation and significantly reduced cost of GREAT Score when compared to the attack-based model ranking on RobustBench. GREAT Score can be used for remote auditing of privacy-sensitive black-box models.
  arXiv  Detail & Related papers  (2023-04-19T14:58:27Z)
• MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion [8.338999282303755]
  We propose a novel algorithm based on the Swin Transformer. It aggregates information from both local and global features to better predict the quality. It ranks 2nd in the no-reference track of NTIRE 2022 Perceptual Image Quality Assessment Challenge.
  arXiv  Detail & Related papers  (2022-05-20T11:34:35Z)
• MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment [18.637040004248796]
  No-Reference Image Quality Assessment (NR-IQA) aims to assess the perceptual quality of images in accordance with human subjective perception. Existing NR-IQA methods are far from meeting the needs of predicting accurate quality scores on GAN-based distortion images. We propose Multi-dimension Attention Network for no-reference Image Quality Assessment (MANIQA) to improve the performance on GAN-based distortion.
  arXiv  Detail & Related papers  (2022-04-19T15:56:43Z)
• Learning Transformer Features for Image Quality Assessment [53.51379676690971]
  We propose a unified IQA framework that utilizes CNN backbone and transformer encoder to extract features. The proposed framework is compatible with both FR and NR modes and allows for a joint training scheme.
  arXiv  Detail & Related papers  (2021-12-01T13:23:00Z)
• MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment [73.55944459902041]
  This paper presents a no-reference IQA metric based on deep meta-learning. We first collect a number of NR-IQA tasks for different distortions. Then meta-learning is adopted to learn the prior knowledge shared by diversified distortions. Extensive experiments demonstrate that the proposed metric outperforms the state-of-the-arts by a large margin.
  arXiv  Detail & Related papers  (2020-04-11T23:36:36Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.