衰减解耦机制的图像分类网络

袁姮; 杨继真; 张晟翀

doi:10.12263/DZXB.20250940

您当前的位置：

首页 >

文章列表页 >

衰减解耦机制的图像分类网络

学术论文 | 更新时间：2026-05-28

- 衰减解耦机制的图像分类网络
- Image Classification Network with Attenuation Disentangling Mechanism
- 电子学报 2026年54卷第2期页码：818-836
- 作者机构：
  
  1.辽宁工程技术大学软件学院，辽宁葫芦岛 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：
  
  [ "袁姮女，1988年2月出生于湖北省黄冈市。现为辽宁工程技术大学软件学院副教授。主要研究方向为图像与视觉信息计算、模式识别与人工智能。E-mail: lntuyuanheng@163.com" ]
  [ "杨继真女，2002年7月出生于河南省南阳市。现为辽宁工程技术大学软件学院硕士研究生。主要研究方向为图像与视觉信息计算、模式识别与人工智能。E-mail: 2444603170@qq.com" ]
  [ "张晟翀男，1973年4月出生于安徽省合肥市。高级工程师。主要研究方向为数字信号处理、模式识别与人工智能。E-mail: zsc417@126.com" ]
- 基金信息：
  
  国家自然科学基金(61601213);辽宁省教育厅重点基金(LJYL049);辽宁省教育厅重点项目(LJ2017QL034)
- DOI：10.12263/DZXB.20250940
  中图分类号： TP391;
- 收稿：2025-12-03，
  
  录用：2025-12-31，
  
  纸质出版：2026-02-25
- 稿件说明：
移动端阅览
袁姮, 杨继真, 张晟翀. 衰减解耦机制的图像分类网络[J]. 电子学报, 2026, 54(02): 818-836.

YUAN Heng, YANG Jizhen, ZHANG Shengchong. Image Classification Network with Attenuation Disentangling Mechanism[J]. Acta Electronica Sinica, 2026, 54(02): 818-836.
袁姮, 杨继真, 张晟翀. 衰减解耦机制的图像分类网络[J]. 电子学报, 2026, 54(02): 818-836. DOI：10.12263/DZXB.20250940

YUAN Heng, YANG Jizhen, ZHANG Shengchong. Image Classification Network with Attenuation Disentangling Mechanism[J]. Acta Electronica Sinica, 2026, 54(02): 818-836. DOI：10.12263/DZXB.20250940

摘要

针对图像分类网络提取到的特征耦合度高、判别性不足导致关键特征表达能力受限的问题，本文提出一种衰减解耦机制的图像分类网络（image classification Network with Attenuation Disentangling Mechanism，ADMNet）。首先，基于生物神经元对信号强度的差异化响应特性，提出衰减解耦机制，设计空间衰减解耦（Spatial Attenuation Disentangling，SAD）模块，将特征图分解至独立子空间并进行不同阈值的衰减变换，有效解耦提纯关键特征，过滤空间冗余信息；设计通道解耦（Channel Disentangling，CD）模块，使用多尺度一维卷积建模不同范围的通道耦合关系，动态增强与类别相关的特征通道，抑制无关通道；再整合SAD与CD模块，构建特征衰减解耦（Feature Attenuation Disentangling，FAD）模块，通过双分支联合操作实现特征的有效解耦，增强关键特征的判别性，进而提高图像特征的非线性表达能力。然后，构建特征聚合池化（Feature Aggregation Pooling，FAP）模块，通过聚合不同卷积提取到的多尺度特征，丰富特征表示，提高空间信息利用率，减小特征图尺寸。最后，将FAD模块和FAP模块分别嵌入到残差块的主干路径和残差分支中，让网络学习耦合度更低、判别性更强的特征以及丰富的上下文信息，减少网络传递过程中的信息丢失，提升网络泛化能力。本文方法在CIFAR-10、CIFAR-100、SVHN、Imagenette和Imagewoof数据集上分别取得了96.6%、80.6%、97.5%、89.6%和83.1%的分类准确率。实验结果表明，ADMNet能够有效解耦图像特征，增强特征的判别性，减少信息丢失风险，提升图像分类能力。

Abstract

To address the issue of high entangling and insufficient discriminative ability of the features extracted by image classification networks

which limits the expressive power of key features

this paper proposes an image classification network with attenuation disentangling mechanism (ADMNet). Firstly

based on the differential response characteristics of biological neurons to signal intensity

an attenuation disentangling mechanism is proposed: the spatial attenuation disentangling (SAD) module is designed to decompose the feature map into independent subspaces and perform attenuation transformation with different thresholds

effectively disentangling and purifying key features and filtering redundant information; the channel disentangling (CD) module is designed to use multi-scale one-dimensional convolution to model the channel entangling relationships within different ranges

dynamically enhancing feature channels related to classifications and suppressing irrelevant channels; then

by integrating the SAD and CD modules

the feature attenuation disentangling (FAD) module is formed

which achieves effective disentangling of image features through the joint operation of dual-branches

enhancing the discriminability of key features

and thereby improving the nonlinear expression ability of image features. Then

a feature aggregation pooling (FAP) module is constructed. It aggregates multi-scale features extracted by different convolutions

enriches feature representations

improves spatial information utilization

and reduces the size of feature maps. Finally

the FAD and FAP modules are embedded into the main path and residual branches of the residual block

respectively

allowing the network to learn features with lower coupling and stronger discriminability

as well as rich contextual information. This reduces information loss during network transmission and enhances the network’s generalization ability. The method proposed in this paper achieves classification accuracies of 96.6%

80.6%

97.5%

89.6%

and 83.1% on CIFAR-10

CIFAR-100

SVHN

Imagenette

and Imagewoof datasets

respectively. Experimental results show that ADMNet can effectively decouple image features

enhance feature discriminability

reduce the risk of information loss

and improve image classification ability.

关键词

Keywords

references

Lecun Y , Bottou L , Bengio Y , et al . Gradient-based learning applied to document recognition [J ] . Proceedings of the IEEE , 1998 , 86 ( 11 ): 2278 - 2324 . DOI: 10.1109/5.726791 http://dx.doi.org/10.1109/5.726791

Krizhevsky A , Sutskever I , Hinton G E . ImageNet classification with deep convolutional neural networks [J ] . Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 . DOI: 10.1145/3065386 http://dx.doi.org/10.1145/3065386

Simonyan K , Zisserman A . Very deep convolutional networks for large-scale image recognition [PP/OL ] . V6.arXiv ( 2015-04-10 )[ 2025-12-20 ] . https://arXiv.org/abs/1409.1556 https://arXiv.org/abs/1409.1556 .

Szegedy C , Liu Wei , Jia Yangqing , et al . Going deeper with convolutions [C ] // Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2015 : 7298594 . DOI: 10.1109/cvpr.2015.7298594 http://dx.doi.org/10.1109/cvpr.2015.7298594

He Kaiming , Zhang Xiangyu , Ren Shaoqing , et al . Deep residual learning for image recognition [C ] // Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2016 : 770 - 778 . DOI: 10.1109/cvpr.2016.90 http://dx.doi.org/10.1109/cvpr.2016.90

Khan S , Naseer M , Hayat M , et al . Transformers in vision: A survey [J ] . ACM Computing Surveys , 2022 , 54 ( 10 s): 1 - 41 . DOI: 10.1145/3505244 http://dx.doi.org/10.1145/3505244

Touvron H , Cord M , Douze M , et al . Training data-efficient image transformers & distillation through attention [C ] // Proceedings of the 38th International Conference on Machine Learning . PMLR , 2021 : 10347 - 10357 . DOI: 10.1109/iccv48922.2021.00091 http://dx.doi.org/10.1109/iccv48922.2021.00091

Liu Ze , Lin Yutong , Cao Yue , et al . Swin transformer: Hierarchical vision transformer using shifted windows [C ] // Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision . Piscataway : IEEE , 2022 : 9992 - 10002 . DOI: 10.1109/iccv48922.2021.00986 http://dx.doi.org/10.1109/iccv48922.2021.00986

Xu Wanlu , Liu Hong , Shi Wei , et al . Adversarial feature disentanglement for long-term person re-identification [C ] // Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence . California : IJCAI.org , 2021 : 1201 - 1207 . DOI: 10.24963/ijcai.2021/166 http://dx.doi.org/10.24963/ijcai.2021/166

Liu Dongnan , Zhang Chaoyi , Song Yang , et al . Decompose to adapt: Cross-domain object detection via feature disentanglement [J ] . IEEE Transactions on Multimedia , 2023 , 25 : 1333 - 1344 . DOI: 10.1109/tmm.2022.3141614 http://dx.doi.org/10.1109/tmm.2022.3141614

唐珺琨 , 张辉 , 张邹铨 , 等 . 基于任务关联特征解耦网络的无监督领域自适应图像分类 [J ] . 计算机科学 , 2023 , 50 ( 增刊2 ): 293 - 300 .

Tang Junkun , Zhang Hui , Zhang Zouquan , et al . Image classification for unsupervised domain adaptation based on task relevant feature separation network [J ] . Computer Science , 2023 , 50 ( S2 ): 293 - 300 . (in Chinese)

Yuan Jianjun , Wu Fujun , Zhao Luoming , et al . MLFD: Multi-level feature disentanglement robust network with a novel maximum-minimum algorithm for medical image recognition [J ] . Expert Systems with Applications , 2025 , 294 : 128815 . DOI: 10.1016/j.eswa.2025.128815 http://dx.doi.org/10.1016/j.eswa.2025.128815

Jiang Wentao , Yuan Heng , Liu Wanjun . Neuron signal attenuation activation mechanism for deep learning [J ] . Patterns , 2025 , 6 ( 1 ): 101117 . DOI: 10.1016/j.patter.2024.101117 http://dx.doi.org/10.1016/j.patter.2024.101117

Chen L C , Papandreou G , Schroff F , et al . Rethinking atrous convolution for semantic image segmentation [PP/OL ] . V3. arXiv ( 2017-12-05 )[ 2025-12-20 ] . https://arXiv.org/abs/1706.05587 https://arXiv.org/abs/1706.05587 . DOI: 10.1007/978-3-030-01234-2_49 http://dx.doi.org/10.1007/978-3-030-01234-2_49

Tan Mingxing , Le Q V . EfficientNet: Rethinking model scaling for convolutional neural networks [C ] // Proceedings of the 36th International Conference on Machine Learning . Long Beach : PMLR , 2019 : 6105 - 6114 . DOI: 10.48550/arXiv.1905.11946 http://dx.doi.org/10.48550/arXiv.1905.11946

Han Kai , Wang Yunhe , Tian Qi , et al . GhostNet: More features from cheap operations [C ] // Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2020 : 1577 - 1586 . DOI: 10.1109/cvpr42600.2020.00165 http://dx.doi.org/10.1109/cvpr42600.2020.00165

Huang Gao , Liu Zhuang , Van Der Maaten L , et al . Densely connected convolutional networks [C ] // Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2017 : 2261 - 2269 . DOI: 10.1109/cvpr.2017.243 http://dx.doi.org/10.1109/cvpr.2017.243

Zhou Chenlin , Zhang Han , Zhou Zhaokun , et al . QKFormer: Hierarchical spiking transformer using Q-K attention [C ] // Proceedings of the 38th International Conference on Neural Information Processing Systems . New York : Curran Associates Inc. , 2024 : 13074 - 13098 . DOI: 10.52202/079017-0416 http://dx.doi.org/10.52202/079017-0416

Zagoruyko S , Komodakis N . Wide residual networks [PP/OL ] . V4. arXiv ( 2017-06-14 )[ 2025-12-20 ] . https://arXiv.org/abs/1605.07146 https://arXiv.org/abs/1605.07146 . DOI: 10.5244/c.30.87 http://dx.doi.org/10.5244/c.30.87

Lan Hai , Wang Xihao , Shen Hao , et al . Couplformer: Rethinking vision transformer with coupling attention [C ] // Proceedings of the 2023 IEEE/CVF Winter Conference on Applications of Computer Vision . Piscataway : IEEE , 2023 : 6464 - 6473 . DOI: 10.1109/wacv56688.2023.00641 http://dx.doi.org/10.1109/wacv56688.2023.00641

Hasanpour S H , Rouhani M , Fayyaz M , et al . Towards principled design of deep convolutional networks: Introducing SimpNet [PP/OL ] . V1. arXiv ( 2018-02-17 )[ 2025-12-20 ] . https://arXiv.org/abs/1802.06205 https://arXiv.org/abs/1802.06205 .

Qiu Xuerui , Zhu Ruijie , Yuhong Chou , et al . Gated attention coding for training high-performance and efficient spiking neural networks [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2024 , 38 ( 1 ): 601 - 610 . DOI: 10.1609/aaai.v38i1.27816 http://dx.doi.org/10.1609/aaai.v38i1.27816

Konstantinidis D , Papastratis I , Dimitropoulos K , et al . Multi-manifold attention for vision transformers [J ] . IEEE Access , 2023 , 11 : 123433 - 123444 . DOI: 10.1109/access.2023.3329952 http://dx.doi.org/10.1109/access.2023.3329952

Shin H , Choi D W . Teacher as a lenient expert: Teacher-agnostic data-free knowledge distillation [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2024 , 38 ( 13 ): 14991 - 14999 . DOI: 10.1609/aaai.v38i13.29420 http://dx.doi.org/10.1609/aaai.v38i13.29420

Ma Chenxiang , Wu Jibin , Si Chenyang , et al . Scaling supervised local learning with augmented auxiliary networks [C ] // Proceedings of the Twelfth International Conference on Learning Representations . OpenReview . net , 2024 . https://arxiv.org/pdf/2402.17318 https://arxiv.org/pdf/2402.17318

Choromanski K M , Likhosherstov V , Dohan D , et al . Rethinking attention with performers [C ] // Proceedings of the 9th International Conference on Learning Representations . OpenReview . net , 2021 .

Wu Xidong , Gao Shangqian , Zhang Zeyu , et al . Auto- train-once: Controller network guided automatic network pruning from scratch [C ] // Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2024 : 16163 - 16173 . DOI: 10.1109/cvpr52733.2024.01530 http://dx.doi.org/10.1109/cvpr52733.2024.01530

Yuan Heng , Liu Jie , Jiang Wentao , et al . Double-pooling residual classification network based on feature reordering attention mechanism [J ] . Journal of Image and Graphics , 2025 , 30 ( 1 ): 110 - 129 . DOI: 10.11834/jig.240061 http://dx.doi.org/10.11834/jig.240061

Zhang Xiangyu , Zhou Xinyu , Lin Mengxiao , et al . ShuffleNet: An extremely efficient convolutional neural network for mobile devices [C ] // Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 6848 - 6856 . DOI: 10.1109/cvpr.2018.00716 http://dx.doi.org/10.1109/cvpr.2018.00716

Sandler M , Howard A , Zhu Menglong , et al . MobileNetV2: Inverted residuals and linear bottlenecks [C ] // Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 4510 - 4520 . DOI: 10.1109/cvpr.2018.00474 http://dx.doi.org/10.1109/cvpr.2018.00474

Samek W , Binder A , Montavon G , et al . Evaluating the visualization of what a deep neural network has learned [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2017 , 28 ( 11 ): 2660 - 2673 . DOI: 10.1109/tnnls.2016.2599820 http://dx.doi.org/10.1109/tnnls.2016.2599820

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

全局依赖引导的特征重构图像分类网络

背景感知机制的图像分类网络

基于注意力融合多尺度特征的解压缩点云质量增强方法

执行器攻击下开放式异构多智能体系统的自适应输出一致性

基于信息融合的区块链系统隐匿安全补丁识别及迁移技术