Modulation Recognition Method Based on Improved Res2Net and Adaptive Multi-Scale Window Pooling

WANG Dan; LI Wanjie; JIANG Fengyang

doi:10.12263/DZXB.20251229

您当前的位置：

首页 >

文章列表页 >

Modulation Recognition Method Based on Improved Res2Net and Adaptive Multi-Scale Window Pooling

PAPERS | 更新时间：2026-05-28

- Modulation Recognition Method Based on Improved Res2Net and Adaptive Multi-Scale Window Pooling
- ACTA ELECTRONICA SINICA Vol. 54, Issue 2, Pages: 562-577(2026)
- 作者机构：
  
  重庆邮电大学通信与信息工程学院，重庆 400065
- 作者简介：
- 基金信息：
  
  Innovation and Development Joint Fund of Chongqing Natural Science Foundation (China Satellite Network)(CSTB2023NSCQ-LZX0114)
- DOI：10.12263/DZXB.20251229
  CLC： TN911.3;
- Received：12 January 2026，
  
  Accepted：31 January 2026，
  
  Published：25 February 2026
- 稿件说明：
移动端阅览
王丹, 李万杰, 江丰杨. 基于改进Res2Net与自适应多尺度窗口池化的调制识别方法[J]. 电子学报, 2026, 54(02): 562-577.

WANG Dan, LI Wanjie, JIANG Fengyang. Modulation Recognition Method Based on Improved Res2Net and Adaptive Multi-Scale Window Pooling[J]. Acta Electronica Sinica, 2026, 54(02): 562-577.
王丹, 李万杰, 江丰杨. 基于改进Res2Net与自适应多尺度窗口池化的调制识别方法[J]. 电子学报, 2026, 54(02): 562-577. DOI：10.12263/DZXB.20251229

WANG Dan, LI Wanjie, JIANG Fengyang. Modulation Recognition Method Based on Improved Res2Net and Adaptive Multi-Scale Window Pooling[J]. Acta Electronica Sinica, 2026, 54(02): 562-577. DOI：10.12263/DZXB.20251229

摘要

随着现代通信技术的快速发展，自动调制识别（Automatic Modulation Recognition，AMR）在频谱资源管理方面的重要性日益凸显，基于深度学习的AMR方法凭借其优异的性能成为当前研究热点。针对现有方法在复杂信道条件下多尺度特征融合能力不足、特征token化方式有效性与复杂度难以平衡的问题，提出一种基于改进Res2Net与自适应多尺度窗口池化的调制识别方法Res2-AMWP。特征提取阶段利用改进的Res2Net对特征按通道分组并逐级融合，同时引入挤压与激励（Squeeze-and-Excitation，SE）注意力机制对通道进行自适应重标定。特征融合阶段提出自适应多尺度窗口池化（Adaptive Multi-scale Window Pooling，AMWP）模块将多尺度特征转化为更具判别性的token表征，并利用双向长短期记忆网络（Bidirectional Long Short-Term Memory，BiLSTM）捕获token间的上下文依赖。注意力分类头采用注意力池化机制进一步突出关键的token表征，由全连接层得到最终的识别结果。在公开数据集RadioML2016.10a、RadioML2016.10b、RML22上的实验结果表明，Res2-AMWP的整体识别准确率分别达到63.51%、65.36%、70.30%，相较于多种对比方法分别提高了1.01%~7.33%、0.32%~6.5%、0.75%~8.40%，且模型的复杂度保持在较低水平，实现了精度与复杂度的较好平衡。

Abstract

With the rapid development of modern communication technology

automatic modulation recognition (AMR) has become increasingly important in spectrum resource management

and deep learning-based AMR methods have become a current research hotspot due to their superior performance. To address the problems of insufficient multi-scale feature fusion capability and the difficulty in balancing the effectiveness and complexity of feature tokenization under complex channel conditions in existing methods

this thesis proposed a modulation recognition method termed Res2-AMWP based on an improved Res2Net and adaptive multi-scale window pooling. In the feature extraction stage

the improved Res2Net was adopted to group features by channel and fuse them progressively

while the squeeze-and-excitation (SE) attention mechanism was introduced to perform adaptive channel re-calibration. In the feature fusion stage

an adaptive multi-scale window pooling (AMWP) module was proposed to transform multi-scale features into more discriminative token representations

and a bidirectional long short-term memory network (BiLSTM) was employed to capture contextual dependencies among tokens. The attention-based classification head further highlighted key token representations through an attention pooling mechanism

and the final recognition results were obtained by fully connected layers. Experimental results on the public datasets RadioML2016.10a

RadioML2016.10b

and RML22 demonstrated that Res2-AMWP achieved overall recognition accuracies of 63.51%

65.36%

and 70.30%

respectively

outperforming multiple baseline methods by 1.01%~7.33%

0.32%~6.5%

and 0.75%~8.40% on the three datasets. Moreover

the model complexity remained at a relatively low level

achieving a good balance between accuracy and complexity.

关键词

Keywords

references

Kong Weisi , Jiao Xun , Xu Yuhua , et al . A transformer-based contrastive semi-supervised learning framework for automatic modulation recognition [J ] . IEEE Transactions on Cognitive Communications and Networking , 2023 , 9 ( 4 ): 950 - 962 . DOI: 10.1109/tccn.2023.3264908 http://dx.doi.org/10.1109/tccn.2023.3264908

Zhang Jiawei , Wang Tiantian , Feng Zhixi , et al . Toward the automatic modulation classification with adaptive wavelet network [J ] . IEEE Transactions on Cognitive Communications and Networking , 2023 , 9 ( 3 ): 549 - 563 . DOI: 10.1109/tccn.2023.3252580 http://dx.doi.org/10.1109/tccn.2023.3252580

郑庆河 , 刘方霖 , 余礼苏 , 等 . 基于改进Kolmogorov-Arnold混合卷积神经网络的调制识别方法 [J ] . 电子与信息学报 , 2025 , 47 ( 8 ): 2584 - 2597 .

Zheng Qinghe , Liu Fanglin , Yu Lisu , et al . An improved modulation recognition method based on hybrid Kolmogorov-Arnold convolutional neural network [J ] . Journal of Electronics & Information Technology , 2025 , 47 ( 8 ): 2584 - 2597 . (in Chinese)

Hao Xiaoyang , Feng Zhixi , Yang Shuyuan , et al . Automatic modulation classification via meta-learning [J ] . IEEE Internet of Things Journal , 2023 , 10 ( 14 ): 12276 - 12292 . DOI: 10.1109/jiot.2023.3247162 http://dx.doi.org/10.1109/jiot.2023.3247162

Liu Fugang , Pan Jingyi , Zhou Ruolin . Contrastive learning-based multimodal fusion model for automatic modulation recognition [J ] . IEEE Communications Letters , 2024 , 28 ( 1 ): 78 - 82 . DOI: 10.1109/lcomm.2023.3336049 http://dx.doi.org/10.1109/lcomm.2023.3336049

Zheng Jianping , Lyu Yanfang . Likelihood-based automatic modulation classification in OFDM with index modulation [J ] . IEEE Transactions on Vehicular Technology , 2018 , 67 ( 9 ): 8192 - 8204 . DOI: 10.1109/tvt.2018.2839735 http://dx.doi.org/10.1109/tvt.2018.2839735

Majhi S , Gupta R , Xiang Weidong , et al . Hierarchical hypothesis and feature-based blind modulation classification for linearly modulated signals [J ] . IEEE Transactions on Vehicular Technology , 2017 , 66 ( 12 ): 11057 - 11069 . DOI: 10.1109/tvt.2017.2727858 http://dx.doi.org/10.1109/tvt.2017.2727858

Chang Shuo , Yang Zheng , He Jiashuo , et al . A fast multi-loss learning deep neural network for automatic modulation classification [J ] . IEEE Transactions on Cognitive Communications and Networking , 2023 , 9 ( 6 ): 1503 - 1518 . DOI: 10.1109/tccn.2023.3309010 http://dx.doi.org/10.1109/tccn.2023.3309010

An T T , Lee B M . Robust automatic modulation classification in low signal to noise ratio [J ] . IEEE Access , 2023 , 11 : 7860 - 7872 . DOI: 10.1109/access.2023.3238995 http://dx.doi.org/10.1109/access.2023.3238995

Li Lin , Zhu Yaxin , Zhu Zhigang . Automatic modulation classification using ResNeXt-GRU with deep feature fusion [J ] . IEEE Transactions on Instrumentation and Measurement , 2023 , 72 : 2519710 . DOI: 10.1109/tim.2023.3290301 http://dx.doi.org/10.1109/tim.2023.3290301

O’Shea T J , Corgan J , Clancy T C . Convolutional radio modulation recognition networks [C ] // Engineering Applications of Neural Networks . Cham : Springer , 2016 : 213 - 226 . DOI: 10.1007/978-3-319-44188-7_16 http://dx.doi.org/10.1007/978-3-319-44188-7_16

Hong Dehua , Zhang Zilong , Xu Xiaodong . Automatic modulation classification using recurrent neural networks [C ] // 2017 3rd IEEE International Conference on Computer and Communications (ICCC) . Piscataway : IEEE , 2018 : 695 - 700 . DOI: 10.1109/compcomm.2017.8322633 http://dx.doi.org/10.1109/compcomm.2017.8322633

O’Shea T J , West N . Radio machine learning dataset generation with GNU Radio [C ] // Proceedings of the 6th GNU Radio Conference . Boulder : The GNU Radio Foundation , 2016 : 1 - 6 .

Zhang Zufan , Luo Hao , Wang Chun , et al . Automatic modulation classification using CNN-LSTM based dual-stream structure [J ] . IEEE Transactions on Vehicular Technology , 2020 , 69 ( 11 ): 13521 - 13531 . DOI: 10.1109/tvt.2020.3030018 http://dx.doi.org/10.1109/tvt.2020.3030018

Huang Sai , Dai Rui , Huang Juanjuan , et al . Automatic modulation classification using gated recurrent residual network [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 8 ): 7795 - 7807 . DOI: 10.1109/jiot.2020.2991052 http://dx.doi.org/10.1109/jiot.2020.2991052

Zhang Hao , Zhou Fuhui , Wu Qihui , et al . A novel automatic modulation classification scheme based on multi-scale networks [J ] . IEEE Transactions on Cognitive Communications and Networking , 2022 , 8 ( 1 ): 97 - 110 . DOI: 10.1109/tccn.2021.3091730 http://dx.doi.org/10.1109/tccn.2021.3091730

Tan Haoyue , Zhang Zhenxi , Li Yu , et al . Multi-scale feature fusion and distribution similarity network for few-shot automatic modulation classification [J ] . IEEE Signal Processing Letters , 2024 , 31 : 2890 - 2894 . DOI: 10.1109/lsp.2024.3470762 http://dx.doi.org/10.1109/lsp.2024.3470762

Dao T T , Noh D I , Pham Q V , et al . VT-MCNet: High-accuracy automatic modulation classification model based on vision transformer [J ] . IEEE Communications Letters , 2024 , 28 ( 1 ): 98 - 102 . DOI: 10.1109/lcomm.2023.3336985 http://dx.doi.org/10.1109/lcomm.2023.3336985

O’Shea T J , Roy T , Clancy T C . Over-the-air deep learning based radio signal classification [J ] . IEEE Journal of Selected Topics in Signal Processing , 2018 , 12 ( 1 ): 168 - 179 . DOI: 10.1109/jstsp.2018.2797022 http://dx.doi.org/10.1109/jstsp.2018.2797022

Cai Jingjing , Gan Fengming , Cao Xianghai , et al . Signal modulation classification based on the transformer network [J ] . IEEE Transactions on Cognitive Communications and Networking , 2022 , 8 ( 3 ): 1348 - 1357 . DOI: 10.1109/tccn.2022.3176640 http://dx.doi.org/10.1109/tccn.2022.3176640

Gao Shanghua , Cheng Mingming , Zhao Kai , et al . Res2Net: A new multi-scale backbone architecture [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2021 , 43 ( 2 ): 652 - 662 . DOI: 10.1109/tpami.2019.2938758 http://dx.doi.org/10.1109/tpami.2019.2938758

Hu Jie , Shen Li , Sun Gang . Squeeze-and-excitation networks [C ] // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Piscataway : IEEE , 2018 : 7132 - 7141 . DOI: 10.1109/cvpr.2018.00745 http://dx.doi.org/10.1109/cvpr.2018.00745

Sathyanarayanan V , Gerstoft P , El Gamal A . RML22: Realistic dataset generation for wireless modulation classification [J ] . IEEE Transactions on Wireless Communications , 2023 , 22 ( 11 ): 7663 - 7675 . DOI: 10.1109/twc.2023.3254490 http://dx.doi.org/10.1109/twc.2023.3254490

Xu Jialang , Luo Chunbo , Parr G , et al . A spatiotemporal multi-channel learning framework for automatic modulation recognition [J ] . IEEE Wireless Communications Letters , 2020 , 9 ( 10 ): 1629 - 1632 . DOI: 10.1109/lwc.2020.2999453 http://dx.doi.org/10.1109/lwc.2020.2999453

Rajendran S , Meert W , Giustiniano D , et al . Deep learning models for wireless signal classification with distributed low-cost spectrum sensors [J ] . IEEE Transactions on Cognitive Communications and Networking , 2018 , 4 ( 3 ): 433 - 445 . DOI: 10.1109/tccn.2018.2835460 http://dx.doi.org/10.1109/tccn.2018.2835460

Zhang Jiawei , Wang Tiantian , Feng Zhixi . AMC-Net: An effective network for automatic modulation classification [C ] // ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing . Piscataway : IEEE , 2023 : 10097070 . DOI: 10.1109/icassp49357.2023.10097070 http://dx.doi.org/10.1109/icassp49357.2023.10097070

Feng Yuan , Peng Kexiao , Wei Jiaolong , et al . Window attention convolution network (WACN): A local self-attention automatic modulation recognition method [J ] . IEEE Transactions on Cognitive Communications and Networking , 2025 , 11 ( 3 ): 1597 - 1608 . DOI: 10.1109/tccn.2024.3462905 http://dx.doi.org/10.1109/tccn.2024.3462905

Liu Xiaoyu , Yang Diyu , El Gamal A . Deep neural network architectures for modulation classification [C ] // 2017 51st Asilomar Conference on Signals, Systems, and Computers . Piscataway : IEEE , 2017 : 915 - 919 . DOI: 10.1109/acssc.2017.8335483 http://dx.doi.org/10.1109/acssc.2017.8335483

Huynh-The T , Hua C H , Pham Q V , et al . MCNet: An efficient CNN architecture for robust automatic modulation classification [J ] . IEEE Communications Letters , 2020 , 24 ( 4 ): 811 - 815 . DOI: 10.1109/lcomm.2020.2968030 http://dx.doi.org/10.1109/lcomm.2020.2968030

Zhang Fuxin , Luo Chunbo , Xu Jialang , et al . An efficient deep learning model for automatic modulation recognition based on parameter estimation and transformation [J ] . IEEE Communications Letters , 2021 , 25 ( 10 ): 3287 - 3290 . DOI: 10.1109/lcomm.2021.3102656 http://dx.doi.org/10.1109/lcomm.2021.3102656

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Semantic Segmentation of Remote Sensing Image Based on Multi-Scale Semantic Encoder-Decoder Network

Automatic Modulation Recognition Method via Conceal-Truth-While-Showing-Fake Strategy in Non-Cooperative Adversarial Scenarios

Pedestrian Trajectory Prediction Based on Graph Convolution and Adaptive Transformer

Sequence-Based and Cross-Modal Alignment Model for Protein Function Prediction

Resource Allocation for Mutualistic Symbiotic Radio with Hybrid Long-Short Packets Transmissions

Related Author

LIANG Yan

YI Chun-xia

WANG Guang-yu

HU Yue-hui

YIN Zhisheng

ZHANG Zhijie

CHENG Nan

LIU Yiliang

Related Institution

School of Communication and Information Engineering， Chongqing University of Posts and Telecommunications

Chongqing Key Laboratory of Signal and Information Processing

Engineering Research Center of Mobile Communications of the Ministry of Education

School of Telecommunications Engineering, Xidian University

State Key Laboratory of Integrated Services Networks

⁰