Hybrid CNN-Transformer Architectures

Ask about this topic

Overview

These architectures pair CNNs, which capture local patterns efficiently, with Transformers that model long-range relationships. Common designs use parallel CNN and ViT or Swin branches, Transformer bottlenecks in U-Nets, and gated or cross-attention fusion; some apply lightweight or linear attention to reduce computation. They are used for tasks such as medical-image segmentation, remote-sensing classification, object detection, and physiological-signal analysis, with performance measured on task-specific benchmarks and sometimes across unseen domains. The central tension is whether global context improves accuracy enough to justify added cost: gains are not universal, and well-tuned CNNs can match or outperform hybrids, especially on limited or shifted data.

Latest papers

CardsList

117 papers5 papers in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

  1. ACSAN: All-Convolutional Self-Attention Network Integrating Convolutional Operations with Vision Transformer

    Oct 26, 2026Zimian Wei, Tianqi Zhang, Hengyue PanHybrid CNN-Transformer ArchitecturesEfficient ViTs

    College of Computer Science and Technology, National University of Defense Technology, 109 Deya Road, Changsha, 410073, Hunan, China

  2. Acute Stroke Classification Using Asymmetric Data Standardization and Orthogonal-Focal Loss Optimized CNN-ViT Cross-Attention Fusion: A Multicenter External Validation Study

    Oct 25, 2026Tansel UyarMedical Image ClassificationMedical Imaging

    Department of Biomedical Engineering, Faculty of Engineering, Başkent University, Ankara, 06790, Türkiye

  3. Enhancing Cross-Grade Generalization in Banana Variety Classification via Hybrid CNN-Transformers and Knowledge Self-Distillation

    Oct 21, 2026Khush Kataruka, Mohammad Muzammila, Zahid Akhtar +2ClassificationCross-Domain Generalization

    Department of Artificial Intelligence, Sardar Vallabhbhai National Institute of Technology, Surat, Gujarat, India. · Electrical and Computer Engineering Department, State University of New York Polytechnic Institute, Utica, New York, USA. · Department of Information Security and Communication Technology, Norwegian University of Science and Technology, Gjovik, Norway.

  4. HybridDualPathNet: Cross-Fusion Attention of EfficientNetV2 and Swin Transformer for Brain MRI Classification of Alzheimer's and Parkinson's Disease

    Oct 12, 2026Jarpula Nirjala, Rahul PatelParkinson's Disease ClassificationMedical Image Classification

    Department of Electronics and Communication Engineering, Indian Institute of Information Technology, Surat, India

  5. Why Convolution Still Matters: Evaluating Inductive Biases in Cryospheric Image Classification

    Oct 2, 2026Chhaya Kulkarni, Emam HossainConvolutional Neural NetworksRemote Sensing Image Understanding

    Department of Computer and Information Sciences Towson University · Department of Information Systems University of Maryland, Baltimore County

  6. Cropland PAtteRNS: Parallel Dimensional Attention Networks and Attention to Dataset Disparity for Crop Segmentation in Satellite Imagery Time Series Data

    Sep 29, 2026Joseph Metcalfe, Sara Sharifzadeh, Fabio CaraffiniRemote Sensing Image SegmentationAgricultural Remote Sensing

    Department of Computer Science, Swansea University, Swansea, SA1 8EN, United Kingdom

  7. Lightweight Vision Transformer-Based U-Net for Brain Tumor Segmentation from MRI

    Sep 24, 2026Sheekar Banerjee, Md. Srabon Chowdhury, Md. Mahbub Hasan Akash +1Hybrid CNN-Transformer ArchitecturesVision Transformer

    Department of CSE, IUBAT, Dhaka, Bangladesh

  8. LiAuto-MindViT: A Hybrid Vision Backbone with Adaptive Bidirectional Mamba

    Sep 21, 2026Lifu Mu, Shuai Chen, Wen Zheng +7Hybrid CNN-Transformer ArchitecturesVisual SSMs

    Li Auto Inc. · University of Science and Technology of China

  9. MECT: Mixture of Experts with CNN-Transformer Network for Speaker verification

    Sep 21, 2026Yu Zheng, Jinghan Peng, ChangHao Zhang +2Speaker VerificationHybrid CNN-Transformer Architectures

    Machine Intelligence, Ant Group, Shanghai, China

  10. A Lightweight CNN Integrated Compact Convolutional Transformer for Multi-Scale Feature Learning and reducing computational complexity for breast cancer mammography image detection and classification

    Sep 16, 2026Md Taimur Ahad, Ainuddin AhmedHybrid CNN-Transformer ArchitecturesMedical Image Classification

    Department of Management North South University, Dhaka, Bangladesh

  11. CoAtNet-DeepMoE: A Convolution-Attention Hybrid with DeepSeek Mixture-of-Experts for Parameter-Efficient Tomato Disease Classification

    Sep 16, 2026Md Nadim Mahamood, Md Arif Shahriar, Md Shafi Ud Doula +1Plant Disease ClassificationHybrid CNN-Transformer Architectures

    Department of Computer Science and Engineering Begum Rokeya University Rangpur, Bangladesh · Department of Computer Science Texas State University San Marcos, Texas, USA · Department of Information and Communication Technologies Asian Institute of Technology Pathum Thani, Thailand

  12. WaVeFuse: Regime-Adaptive Equity Index Forecasting via Channel-Wise Wavelet Denoising and Vertical Attention Fusion

    Sep 13, 2026Aashish Bohra, Vivek VijayTime Series ForecastingFinancial Time Series

    Department of Computer Science and Engineering, Indian Institute of Technology Jodhpur, Jodhpur, Rajasthan, India

  13. Schizophrenia Detection from EEG Signals: A Transformer Framework with Spectrogram Representation

    Sep 12, 2026Abtin Shafiei, Mohsen Hooshmand, Majid RamezaniElectroencephalographyHybrid CNN-Transformer Architectures

    Department of Computer Sciences and Information Technology Institute for Advanced Studies in Basic Sciences Zanjan, Iran

  14. TriCCOT: Tri-part Convolutional Conformal Transformer for Onboard Space Object Detection

    Sep 8, 2026Adrien Dorise, Marjorie Bellizzi, Julia Cohen +1Hybrid CNN-Transformer ArchitecturesObject Detection

    Centre National d’Etudes Spatiales, CNES Toulouse, France · IRT Saint-Exupéry Toulouse, France

  15. FreeTransformSR: Efficient Lightweight Image Super-Resolution via Free Low-Rank Learnable Transform

    Sep 5, 2026Hongji Li, Yunhui LiHybrid CNN-Transformer ArchitecturesImage Super-Resolution

    Chinese Academy of Sciences Changchun Institute of Optics Fine Mechanics and Physics, Changchun, Jilin 130033, China · University of the Chinese Academy of Sciences, Beijing 100049, China

  16. What Does the Encoder Actually Decide? A Controlled Comparison of Vision Backbones on Joint Tree Segmentation and Stereo Depth

    Sep 2, 2026Yida Lin, Bing Xue, Mengjie Zhang +2Stereo Depth EstimationImage Segmentation

    Centre for Data Science and Artificial Intelligence Victoria University of Wellington, Wellington, New Zealand · Department of Computer Science and Software Engineering University of Canterbury, Canterbury, New Zealand

  17. Swin Meets EfficientNet: Lightweight Architectures for GAN-Based Face Forensics

    Sep 1, 2026Sejuti Basu, Ashima Sood, Vijay Kumar +1Hybrid CNN-Transformer ArchitecturesEfficient ViTs

    International Institute of Information Technology, Bangalore, India · School of Computing, Engineering, and Intelligent Systems, Ulster University, Londonderry, United Kingdom · Department of Information Technology, Dr B R Ambedkar National Institute of Technology Jalandhar, Punjab, India

  18. U-PAST: A Phase-Aware Audio Spectrogram Transformer-U-Net for Single-Channel Speech Enhancement

    Aug 31, 2026Cao Duong Ly, Jörn AnemüllerHybrid CNN-Transformer ArchitecturesSpeech Enhancement

    Department of Medical Physics and Acoustics Carl von Ossietzky University Oldenburg Oldenburg, Germany 26129

  19. Seasonality-Aware Hybrid Convolutional Transformer for Antarctic Sea Ice Concentration Forecasting

    Aug 31, 2026Danyang Li, John Taylor, Thang Bui +1Hybrid CNN-Transformer ArchitecturesTime Series Forecasting

    School of Computer Science, Australian National University, Canberra, ACT 2601, Australia · Yau Mathematical Sciences Center, Tsinghua University, Beijing, China

  20. Federated Multi-Task Learning for Bladder Tumor Segmentation and MIBC Classification Using a Hybrid CNN-Transformer Architecture

    Aug 31, 2026Malhar Udmale, Divyanshu Dwivedi, Aarohi Dhand +3Hybrid CNN-Transformer ArchitecturesMulti-Task Learning

    Indian Institute of Information Technology Allahabad, Prayagraj, India · Manipal University Jaipur, Jaipur, India · Norwegian University of Science and Technology, Trondheim, Norway

  21. MCSeg: Pre-training and Fine-tuning Volumetric Pyramid Transformer for Multi-modal Cardiac Image Segmentation

    Aug 31, 2026Zhiyu Ye, Hairong Zheng, Tong ZhangCross-Modality Medical Image SegmentationHybrid CNN-Transformer Architectures

    State Key Laboratory of Biomedical Imaging Science and System, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China · Pengcheng Laboratory, Shenzhen, China · University of Chinese Academy of Sciences, Beijing, China

  22. CiUNet: A Hybrid Swin-CNN UNet for Medical Image Segmentation

    Aug 23, 2026Bin Dong, Jinghong ChenMedical Image SegmentationU-Net

    Ciphowork GmbH

  23. Robust Lightweight Deep Learning Models for Oral Cancer Screening

    Aug 21, 2026Siddhant Bharadwaj, Aakash Shedsale, Tejashree Subramanya +6Medical Image ClassificationLightweight CNNs

    Indian Institute of Science · KLES’ Institute of Dental Sciences · Indian Institue of Science +1

  24. When Simplicity Wins: Bottleneck-Aware Context Modeling for Lightweight Semantic Segmentation

    Aug 19, 2026Mian Muhammad Naeem Abid, Nancy Mehta, Zongwei Wu +1Semantic SegmentationHybrid CNN-Transformer Architectures

    Computer Vision Lab, CAIDAS & IFI, University of Würzburg, Germany

  25. OptiModNet: A UNet-Transformer Hybrid with Grouped-Query and Channel Attention for Optic Disc and Cup Segmentation

    Aug 19, 2026Soumili Ghosh, Debapriya Roy, Aryan Das +1Optic Disc SegmentationOphthalmic Image Analysis

    IEM Saltlake,India · Techno Main Salt Lake, India · VIT Bhopal University, India +1

  26. ORViT-DR: Ordinally-Robust Hybrid ViT for Low-Resolution Diabetic Retinopathy Grading

    Aug 16, 2026Soumit Kumar Kundu, Nabil Ashab, Bidhan Biswas +4Diabetic Retinopathy GradingHybrid CNN-Transformer Architectures

    Department of Computer Science and Engineering, Dhaka International University, Dhaka, Bangladesh · KUET, Khulna, Bangladesh · Bangladesh Bank, Dhaka, Bangladesh

  27. "What's That Sound?": A Versatile, Robust, and Lightweight Convolutional Transformer for Environment Sound Recognition

    Aug 16, 2026Julia HuangAudio ClassificationHybrid CNN-Transformer Architectures

    Northville High School, Northville, USA

  28. DualMiT-Net: Local-Global Transformer-Convolutional Fusion for Breast Mass Segmentation in Mammographic Regions of Interest

    Aug 15, 2026Alibek Kamiluly, Milana Muratova, Yash Patel +1Medical Image SegmentationHybrid CNN-Transformer Architectures

    Department of Mathematics and Computer Science, Lawrence Technological University · College of Business and Information Technology, Lawrence Technological University

  29. UniCon-Former: Unified Convolution Transformer is All You Need for Hand Gesture Recognition

    Aug 13, 2026Mallika Garg, Debashis Ghosh, Pyari Mohan PradhanHybrid CNN-Transformer ArchitecturesEfficient ViTs

    Indian Institute of Technology Kharagpur, INDIA · Indian Institute of Technology Roorkee, INDIA

  30. CRHT: A Continuous Regression Hybrid Transformer for Vessel Trajectory Prediction with Online Cluster Sampling

    Aug 10, 2026Alexander Schiøtz, Bertram Hage, Christian Rand +2Hybrid CNN-Transformer ArchitecturesMaritime Surveillance

    Technical University of Denmark Anker Engelunds Vej 101 2800 Kongens Lyngby, Denmark