• Home
  • Search
  • Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment
  • Open Access IconOpen Access
  • Cite Icon31
  • https://doi.org/10.1109/cvpr52688.2022.00576Copy DOI Icon

Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment

  • Jun 1, 2022
  • Yue Cao +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Full-reference (FR) image quality assessment (IQA) evaluates the visual quality of a distorted image by measuring its perceptual difference with pristine-quality reference, and has been widely used in low-level vision tasks. Pairwise labeled data with mean opinion score (MOS) are required in training FR-IQA model, but is time-consuming and cumbersome to collect. In contrast, unlabeled data can be easily collected from an image degradation or restoration process, making it encouraging to exploit unlabeled training data to boost FR-IQA performance. Moreover, due to the distribution inconsistency between labeled and unlabeled data, outliers may occur in unlabeled data, further increasing the training difficulty. In this paper, we suggest to incorporate semi-supervised and positive-unlabeled (PU) learning for exploiting unlabeled data while mitigating the adverse effect of outliers. Particularly, by treating all labeled data as positive samples, PU learning is leveraged to identify negative samples (i.e., outliers) from unlabeled data. Semi-supervised learning (SSL) is further deployed to exploit positive unlabeled data by dynamically generating pseudo-MOS. We adopt a dual-branch network including reference and distortion branches. Furthermore, spatial attention is introduced in the reference branch to concentrate more on the informative regions, and sliced Wasserstein distance is used for robust difference map computation to address the misalignment issues caused by images recovered by GAN models. Extensive experiments show that our method performs favorably against state-of-the-arts on the benchmark datasets PIPAL, KADID-10k, TID2013, LIVE and CSIQ. The source code and model are available at https://github.com/happycaoyue/JSPL.

Similar Papers
  • Conference Article
  • Citations1

Low-discrepancy Sampling for Full Reference Image Quality Assessment Speed Up

  • Jul 18, 2022
  • Jair Galvao +3
  • Book Chapter
  • Citations10

Full Reference Image Quality Assessment: A Survey

  • Jul 21, 2017
  • Baisakhi Sur Phadikar +2
  • Conference Article
  • Citations245

A comprehensive evaluation of full reference image quality assessment algorithms

  • Sep 01, 2012
  • Lin Zhang +3
  • Conference Article
  • Citations2

PA VIF: A passive aggressive visual information fidelity for full reference image quality assessment

  • Nov 01, 2017
  • Xiaoyu Ma +1
  • Conference Article
  • Citations10

Claim Verification under Positive Unlabeled Learning

  • Dec 07, 2020
  • Fan Yang +2
  • Research Article
  • Citations2

Analysis of wavelet-based full reference image quality assessment algorithm

  • Jun 01, 2019
  • Bulletin of Electrical Engineering and Informatics
  • Faizah Mokhtar +3
  • Book Chapter

Research on Influence of Content Diversity on Full-Reference Image Quality Assessment

  • Jan 01, 2020
  • Huiqing Zhang +4
  • Conference Article

Coarse and Fine Structure Combined Model For Full Reference Image Quality Assessment

  • Oct 22, 2021
  • Leyuan Wu +5
  • Conference Article
  • Citations90

An efficient color image quality metric with local-tuned-global model

  • Oct 01, 2014
  • Ke Gu +3
  • Research Article

Enhancing full-reference image quality assessment via dual-attention fusion of global–local features and CLIP-based text prior

  • Mar 11, 2026
  • Journal on Image and Video Processing
  • Mengyao Huang +4
  • Research Article
  • Citations23

Screen content image quality assessment based on convolutional neural networks

  • Dec 31, 2019
  • Journal of Visual Communication and Image Representation
  • Xuhao Jiang +4
  • Research Article
  • Citations255

Quality Evaluation of Image Dehazing Methods Using Synthetic Hazy Images

  • Sep 01, 2019
  • IEEE Transactions on Multimedia
  • Xiongkuo Min +8
  • Research Article
  • Citations1229

Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment.

  • Oct 10, 2017
  • IEEE Transactions on Image Processing
  • Sebastian Bosse +4
  • Conference Article
  • Citations12

Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction

  • Aug 04, 2023
  • Zhangchi Zhu +9
  • Conference Article
  • Citations7

STAR: Noisy Semi-Supervised Transfer Learning for Visual Classification

  • Oct 20, 2021
  • Hasib Zunair +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.