跳到主要导航 跳到搜索 跳到主要内容

Semi-Supervised Blind Image Quality Assessment through Knowledge Distillation and Incremental Learning

  • Wensheng Pan
  • , Timin Gao
  • , Yan Zhang*
  • , Xiawu Zheng
  • , Yunhang Shen
  • , Ke Li
  • , Runze Hu
  • , Yutao Liu
  • , Pingyang Dai
  • *此作品的通讯作者
  • Xiamen University
  • Peng Cheng Laboratory
  • Tencent
  • Ocean University of China

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

Blind Image Quality Assessment (BIQA) aims to simulate human assessment of image quality. It has a great demand for labeled data, which is often insufficient in practice. Some researchers employ unsupervised methods to address this issue, which is challenging to emulate the human subjective system. To this end, we introduce a unified framework that combines semi-supervised and incremental learning to address the mentioned issue. Specifically, when training data is limited, semi-supervised learning is necessary to infer extensive unlabeled data. To facilitate semi-supervised learning, we use knowledge distillation to assign pseudo-labels to unlabeled data, preserving analytical capability. To gradually improve the quality of pseudo labels, we introduce incremental learning. However, incremental learning can lead to catastrophic forgetting. We employ Experience Replay by selecting representative samples during multiple rounds of semi-supervised learning, to alleviate forgetting and ensure model stability. Experimental results show that the proposed approach achieves state-of-the-art performance across various benchmark datasets. After being trained on the LIVE dataset, our method can be directly transferred to the CSIQ dataset. Compared with other methods, it significantly outperforms unsupervised methods on the CSIQ dataset with a marginal performance drop (-0.002) on the LIVE dataset. In conclusion, our proposed method demonstrates its potential to tackle the challenges in real-world production processes.

源语言英语
主期刊名Technical Tracks 14
编辑Michael Wooldridge, Jennifer Dy, Sriraam Natarajan
出版商Association for the Advancement of Artificial Intelligence
页4388-4396
页数9
版本5
ISBN(电子版)1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 1577358872, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879, 9781577358879
DOI
出版状态已出版 - 25 3月 2024
活动38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, 加拿大
期限: 20 2月 2024 → 27 2月 2024

丛书

姓名Proceedings of the AAAI Conference on Artificial Intelligence
编号5
卷38
ISSN(印刷版)2159-5399
ISSN(电子版)2374-3468

会议

会议38th AAAI Conference on Artificial Intelligence, AAAI 2024
国家/地区加拿大
市Vancouver
时期20/02/24 → 27/02/24

学术指纹

探究 'Semi-Supervised Blind Image Quality Assessment through Knowledge Distillation and Incremental Learning' 的科研主题。它们共同构成独一无二的学术指纹。

引用此