ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Continual Learning for Blind Image Quality Assessment

Zhang, Weixia; Li, Dingquan; Ma, Chao; Zhai, Guangtao; Yang, Xiaokang; Ma, Kede*上海交通大学
IEEE Transactions on Pattern Analysis and Machine Intelligence2023-3-1DOI: 10.1109/TPAMI.2022.3178874
30被引14阅读
引用收藏
分享

摘要

The explosive growth of image data facilitates the fast development of image processing and computer vision methods for emerging visual applications, meanwhile introducing novel distortions to processed images. This poses a grand challenge to existing blind image quality assessment (BIQA) models, which are weak at adapting to subpopulation shift. Recent work suggests training BIQA methods on the combination of all available human-rated IQA datasets. However, this type of approach is not scalable to a large number of datasets and is cumbersome to incorporate a newly created dataset as well. In this paper, we formulate continual learning for BIQA, where a model learns continually from a stream of IQA datasets, building on what was learned from previously seen data. We first identify five desiderata in the continual setting with three criteria to quantify the prediction accuracy, plasticity, and stability, respectively. We then propose a simple yet effective continual learning method for BIQA. Specifically, based on a shared backbone network, we add a prediction head for a new dataset and enforce a regularizer to allow all prediction heads to evolve with new data while being resistant to catastrophic forgetting of old data. We compute the overall quality score by a weighted summation of predictions from all heads. Extensive experiments demonstrate the promise of the proposed continual learning method in comparison to standard training techniques for BIQA, with and without experience replay. We made the code publicly available at https://github.com/zwx8981/BIQA_CL.

学科与关键词

关键词
Blind image quality assessmentcontinual learningsubpopulation shift
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Pattern Analysis and Machine Intelligence
发表日期
2023-03-01
卷期
第 45 卷, 第 3 期
页码
2864-2878
DOI
10.1109/TPAMI.2022.3178874
语言
ENGLISH
成果收录
SCIE
资助标注
National Natural Science Foundation of China [61901262, 62071407, U19B2035]; Shanghai Municipal Science and Technology Major Project [2021SHZDZX0102]; Hong Kong RGC Early Career Scheme [9048212]

作者

  • Z

    Zhang, Weixia (第一作者)

    shanghai jiao tong univ

  • L

    Li, Dingquan

查看全部 6 位作者收起作者
  • M

    Ma, Chao

    shanghai jiao tong univ

  • Z

    Zhai, Guangtao

    shanghai jiao tong univ

  • Y

    Yang, Xiaokang

    shanghai jiao tong univ

  • M

    Ma, Kede (通讯)

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417