《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (10): 3091-3100.DOI: 10.11772/j.issn.1001-9081.2024101407

• 人工智能 • 上一篇    

面向重尾噪声图像分类的残差网络学习方法

宫智宇(), 王士同   

  1. 江南大学 人工智能与计算机学院,江苏 无锡 214122
  • 收稿日期:2024-10-09 修回日期:2024-12-22 接受日期:2024-12-27 发布日期:2025-01-06 出版日期:2025-10-10
  • 通讯作者: 宫智宇
  • 作者简介:宫智宇(2000—),男,山西怀仁人,硕士研究生,主要研究方向:神经网络、深度学习
    王士同(1964—),男,江苏扬州人,教授,博士生导师,硕士,主要研究方向:人工智能、模式识别。
  • 基金资助:
    国家自然科学基金资助项目(U20A20228)

Learning method of residual network for heavy-tailed noisy image classification

Zhiyu GONG(), Shitong WANG   

  1. School of Artificial Intelligence and Computer Science,Jiangnan University,Wuxi Jiangsu 214122,China
  • Received:2024-10-09 Revised:2024-12-22 Accepted:2024-12-27 Online:2025-01-06 Published:2025-10-10
  • Contact: Zhiyu GONG
  • About author:GONG Zhiyu, born in 2000, M. S. candidate. His research interests include neural networks, deep learning.
    WANG Shitong, born in 1964, M. S., professor. His research interests include artificial intelligence, pattern recognition.
  • Supported by:
    National Natural Science Foundation of China(U20A20228)

摘要:

针对残差网络(ResNet)在图像分类中容易受未知重尾噪声影响导致识别准确率下降的问题,提出一种多分布重尾噪声自适应残差网络(MHTNA-ResNet)模型。首先,为抑制重尾噪声对最终预测的影响,设计一个多分布重尾噪声自适应层(MHTNA),该层使用多种重尾分布创建噪声模板,扰动干净的训练数据,使ResNet通过训练获得对重尾噪声图像的识别能力;其次,MHTNA在训练中进行自适应训练,使用最大似然估计法求解更新的噪声模板参数,并根据求解参数重新生成噪声模板,控制噪声始终遵循重尾分布;最后,测试时屏蔽MHTNA,对测试图像进行重尾噪声攻击,从而检验模型的抗噪能力。实验结果表明,与PRIME模型相比,面对重尾噪声的攻击,在CIFAR10、CIFAR100和MINI-ImageNet数据集上所提模型的分类准确率分别平均提升了3.86、7.10和5.46个百分点。可见,所提模型可以有效提高ResNet面对重尾噪声干扰时的鲁棒性。

关键词: 重尾噪声, 图像分类, 残差网络, 多分布, 深度学习

Abstract:

To address the problem that image classification accuracy of Residual Network (ResNet) drops due to influence of unknown heavy-tailed noise, a Multi-distribution Heavy-Tailed Noise Adaptive ResNet (MHTNA-ResNet) model was proposed. Firstly, to reduce impact of heavy-tailed noise on final predictions, a Multi-distribution Heavy-Tailed Noise Adaptive layer (MHTNA) was designed, which created noise templates using various heavy-tailed distributions to perturb clean training data, thereby enabling ResNet to get recognition capabilities for heavy-tailed noisy images through training. Secondly, MHTNA was trained adaptively, updated noise template parameters were solved by using the maximum likelihood estimation method, and the noise templates were regenerated according to these parameters, so as to ensure that the noise is always heavy-tailedly distributed. Finally, during testing, the MHTNA was abandoned and heavy-tailed noise attacks were performed to test images, thereby evaluating the model’s capability of noise resistance. Experimental results demonstrate that compared to PRIME model, the proposed model has the classification accuracy improved by an average of 3.86, 7.10 and 5.46 percentage points, respectively, on the CIFAR10, CIFAR100 and MINI-ImageNet datasets facing heavy-tailed noise attacks. It can be seen that the proposed model can improve ResNet’s robustness against heavy-tailed noise interference effectively.

Key words: heavy-tailed noise, image classification, Residual Network (ResNet), multi-distribution, deep learning

中图分类号: