显著性感知的图像分类网络
DOI:
CSTR:
作者:
作者单位:

1.辽宁工程技术大学软件学院葫芦岛125105;2.光电信息控制和安全技术重点实验室天津300308

作者简介:

通讯作者:

中图分类号:

TP391;TN911.73

基金项目:

国家自然科学基金(61601213)、辽宁省教育厅重点基金(LJYL049)、辽宁省自然科学基金


Image classification network with saliency-aware
Author:
Affiliation:

1.School of Software, Liaoning Technical University, Huludao 125105, China; 2.Key Laboratory of Optoelectronic Information Control and Security Technology, Tianjin 300308, China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对图像分类任务中传统卷积缺乏对特征图统计分布的显式建模,导致显著性特征表达不足且易受背景噪声干扰的问题,提出一种显著性感知的图像分类网络(image classification network with saliency-aware, SANet)。SANet以ResNet-34为基线,首先,提出了显著性感知卷积(saliency-aware convolution, SAConv),通过引入Z-score标准化与非线性映射函数,有效增强显著性特征的表达能力,提取更具区分度的特征。其次,提出显著性感知池化(saliency-aware pooling, SP)模块,通过将显著性感知卷积与平均池化相结合,实现对关键信息的筛选与冗余特征的抑制,缓解特征在传递过程中的流失。随后,将显著性感知卷积与显著性感知池化模块融合,构建显著性感知残差块(saliency-aware block, SABlock),实现显著性特征的层间增强与稳定传递,进一步提升网络的特征表达能力与判别性能。最后,提出显著性感知激励(saliency-aware excitation, SAE)模块,通过引入全局统计特征,建模通道间上下文关系,动态调整通道权重,增强网络对关键区域的响应能力,抑制背景噪声干扰,提高网络的泛化性能。在图像数据集CIFAR-10、CIFAR-100、SVHN、Imagenette和Imagewoof上,SANet分别达到了96.87%、81.47%、97.64%、92.43%、85.54%的分类准确率,与其他主流网络相比分别平均提高了1.88%、3.56%、2.2%、3.87%、5.45%,与当前先进的网络模型相比,该显著性感知机制能够增强网络对关键区域的响应能力、抑制背景干扰,并显著提升模型的泛化性能和鲁棒性。

    Abstract:

    To address the limitations of traditional convolutions in image classification tasks—namely their lack of explicit modeling of feature map statistical distributions, which results in insufficient saliency representation and susceptibility to background noise—a saliency-aware image classification network (SANet) is proposed. Based on ResNet-34, SANet integrates three key modules to enhance feature saliency and robustness. The saliency-aware convolution (SAConv) employs Z-score normalization and a nonlinear mapping function to strengthen salient feature representation and extract more discriminative information. The saliency-aware pooling (SP) module combines SAConv with average pooling to filter critical information while suppressing redundancy, mitigating feature loss during propagation. By fusing SAConv and SP, the saliency-aware block (SABlock) achieves inter-layer enhancement and stable transmission of salient features. Finally, the saliency-aware excitation (SAE) module incorporates global statistical information to model inter-channel contextual dependencies, enabling adaptive channel weighting and improving generalization performance. Experiments on CIFAR-10, CIFAR-100, SVHN, Imagenette, and Imagewoof achieved classification accuracies of 96.87%, 81.47%, 97.64%, 92.43%, and 85.54%, respectively, yielding average improvements of 1.88%, 3.56%, 2.20%, 3.87%, and 5.45% over mainstream networks. These results demonstrate that the proposed saliency-aware mechanism effectively enhances the network’s responsiveness to critical regions, suppresses background interference, and significantly improves both generalization and robustness.

    参考文献
    相似文献
    引证文献
引用本文

姜文涛,唐凯文,张晟翀.显著性感知的图像分类网络[J].电子测量与仪器学报,2026,40(9):112-125

复制
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2026-11-13
  • 出版日期:
文章二维码
×
《电子测量与仪器学报》
关于防范虚假编辑部邮件的郑重公告