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. Hybrid CNN-Transformer Architecture for Arabic Speech Emotion Recognition

    Mar 28, 2026Youcef Soufiane Gheffari, Oussama Mustapha Benouddane, Samiya SilarbiSpeech Emotion RecognitionHybrid CNN-Transformer Architectures

    Department of Computer Science, USTO-MB, Oran, Algeria

  2. Hybrid Deep Learning with Temporal Data Augmentation for Accurate Remaining Useful Life Prediction of Lithium-Ion Batteries

    Mar 28, 2026Yun Tian, Guili Wang, Jian Bi +7RUL EstimationLithium-Ion Batteries

    School of Physics and Electronic Information, Anhui Normal University, Wuhu 241002, China · College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China · School of Design, NingboTech University, Ningbo 315100, China +2

  3. DenseSwinV2: Channel Attentive Dual Branch CNN Transformer Learning for Cassava Leaf Disease Classification

    Mar 26, 2026Shah Saood, Saddam Hussain KhanPlant Disease ClassificationHybrid CNN-Transformer Architectures

    Artificial Intelligence Lab, Department of Computer Systems Engineering, University of Engineering and Applied Sciences · Artificial Intelligence Lab, Department of Computer Systems Engineering, University of Engineering and Applied Sciences (UEAS), Swat 19060, Pakistan · Interdisciplinary Research Center for Smart Mobility and Logistics +1

  4. AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments

    Mar 26, 2026Xuzhi Wang, Xinran Wu, Song Wang +23D Scene Completion3D ViTs

    Tianjin Normal University · Zhejiang University · National University of Singapore

  5. LGEST: Dynamic Spatial-Spectral Expert Routing for Hyperspectral Image Classification

    Mar 25, 2026Jiawen Wen, Suixuan Qiu, Zihang Luo +2Hyperspectral Image ClassificationHybrid CNN-Transformer Architectures

    Information Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, 511453, China · Faculty of Geographical Science, Beijing Normal University, Beijing, 100875, China · School of Electronic and Communication Engineering, Guangzhou University, Guangzhou University, Guangzhou, Guangzhou, 510006, China

  6. B-jet Tagging Using a Hybrid Edge Convolution and Transformer Architecture

    Mar 22, 2026Diego F. Vasquez Plaza, Vidya ManianJet TaggingHigh-Energy Physics

    Department of Electrical and Computer Engineering, University of Puerto Rico Mayaguez, PR 00681-9000, USA

  7. Benchmarking CNN-based Models against Transformer-based Models for Abdominal Multi-Organ Segmentation on the RATIC Dataset

    Mar 19, 2026Lukas Bayer, Sheethal Bhat, Andreas MaierMedical Image SegmentationHybrid CNN-Transformer Architectures

    Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg

  8. UCAN: Unified Convolutional Attention Network for Expansive Receptive Fields in Lightweight Super-Resolution

    Mar 12, 2026Cao Thien Tan, Phan Thi Thu Trang, Do Nghiem Duc +3Image Super-ResolutionLightweight CNNs

    Ho Chi Minh City Open University · AI Tech Lab, Ho Chi Minh City University of Technology · Code Mely AI Research Team +3

  9. Combining Microscopy Data and Metadata for Reconstruction of Cellular Traction Forces Using a Hybrid Vision Transformer-U-Net

    Mar 11, 2026Yunfei Huang, Elena Van der Vorst, Alexander Richard +1Microscopy Image AnalysisU-Net

    Fakultät Physik, Technische Universität Dortmund, Dortmund, 44227, Germany. · Faculty of Physics and Center for NanoScience, Ludwig-Maximilians-Universität München, Munich, 80752, Germany. · Department of Veterinary Sciences, Ludwig-Maximilians-Universität München, Munich, 80752, Germany.

  10. Remote Sensing Image Classification Using Deep Ensemble Learning

    Mar 6, 2026Niful Islam, Md. Rayhan Ahmed, Nur Mohammad Fahad +4Remote Sensing Image UnderstandingHybrid CNN-Transformer Architectures

    Department of Computer Science and Engineering, Oakland University, Michigan, USA · Irving K. Barber Faculty of Science, University of British Columbia, Kelowna, Canada · Department of Computer Science and Engineering, United International University, Dhaka, Bangladesh +3

  11. Gated Differential Linear Attention: A Linear-Time Decoder for High-Fidelity Medical Segmentation

    Mar 3, 2026Hongbo Zheng, Afshin Bozorgpour, Dorit Merhof +1Medical Image SegmentationLinear Attention

    University of Illinois Urbana-Champaign · University of Regensburg

  12. MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention

    Mar 2, 2026Zilong Zhao, Zhengming Ding, Pei Niu +2Crack SegmentationHybrid CNN-Transformer Architectures

    School of Qilu Transportation, Shandong University, China · Department of Computer Science, Tulane University, USA

  13. HARU-Net: Hybrid Attention Residual U-Net for Edge-Preserving Denoising in Cone-Beam Computed Tomography

    Feb 26, 2026Khuram Naveed, Ruben PauwelsImage DenoisingLDCT Denoising

    Department of Dentistry and Oral Health, Aarhus University, Aarhus, 8000, Denmark

  14. Le-DETR: Revisiting Real-Time Detection Transformer with Efficient Encoder Design

    Feb 24, 2026Jiannan Huang, Aditya Kane, Fengzhe Zhou +2Real-Time Object DetectionEfficient Object Detection

    Beijing Jiaotong University

  15. Token-UNet: A New Case for Transformers Integration in Efficient and Interpretable 3D UNets for Brain Imaging Segmentation

    Feb 23, 2026Louis Fabrice Tshimanga, Andrea Zanola, Federico Del Pup +13D Medical Image SegmentationHybrid CNN-Transformer Architectures

  16. NeXt2Former-CD: Efficient Remote Sensing Change Detection with Modern Vision Architectures

    Feb 21, 2026Yufan Wang, Sokratis Makrogiannis, Chandra KambhamettuRemote Sensing Change DetectionHybrid CNN-Transformer Architectures

    University of South Florida · Delaware State University

  17. A Hybrid Federated Learning Based Ensemble Approach for Lung Disease Diagnosis Leveraging Fusion of SWIN Transformer and CNN

    Feb 19, 2026Asif Hasan Chowdhury, Md. Fahim Islam, M Ragib Anjum Riad +3Medical DiagnosisChest X-Ray Classification

    BRAC University, Dhaka-1212, Bangladesh

  18. RefineFormer3D: Efficient 3D Medical Image Segmentation via Adaptive Multi-Scale Transformer with Cross Attention Fusion

    Feb 18, 2026Kavyansh Tyagi, Vishwas Rathi, Puneet Goyal3D Medical Image Segmentation3D ViTs

    National Institute of Technology Kurukshetra Department of Electronics and Communication Engineering · National Institute of Technology Kurukshetra Department of Computer Engineering · Indian Institute of Technology Ropar Department of Computer Science and Engineering

  19. UCTECG-Net: Uncertainty-aware Convolution Transformer ECG Network for Arrhythmia Detection

    Feb 18, 2026Hamzeh Asgharnezhad, Pegah Tabarisaadi, Abbas Khosravi +2Electrocardiogram ClassificationHybrid CNN-Transformer Architectures

    Deakin University, Australia . · School of Mathematics, Physics and Computing, University of Southern Queensland, Toowoomba, QLD, Australia .

  20. Categorize Early, Integrate Late: Divergent Processing Strategies in Automatic Speech Recognition

    Jan 11, 2026Nathan Roll, Pranav Bhalerao, Martijn Bartelds +7Audio Representation LearningHybrid CNN-Transformer Architectures

    Stanford University

  21. DuaDeep-SeqAffinity: Dual-Branch Deep Learning for Tri-Stream Sequence-Based Antibody--Antigen Affinity Prediction

    Dec 26, 2025Aicha Boutorh, Soumia Bouyahiaoui, Manel Kara Laouar +3Hybrid CNN-Transformer ArchitecturesMolecular Property Prediction

    National School of Artificial Intelligence (ENSIA) Sidi Abdallah Campus, Algiers, Algeria · Lamine Debaghine University Hospital Center, CHU Bab El Oued, Algiers, Algeria

  22. BrainRotViT: Transformer-ResNet Hybrid for Explainable Modeling of Brain Aging from 3D sMRI

    Nov 19, 2025Wasif Jalal, Md Nafiu Rahman, Atif Hasan Rahman +1Brain Age PredictionBrain MRI

    Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology

  23. Unifying Convolution and Attention via Convolutional Nearest Neighbors

    Nov 18, 2025Mingi Kang, Jeová Farias Sales Rocha NetoHybrid CNN-Transformer ArchitecturesSelf-Attention

    Bowdoin College

  24. Johnson-Lindenstrauss Lemma Guided Network for Efficient 3D Medical Segmentation

    Sep 26, 2025Jinpeng Lu, Linghan Cai, Yinda Chen +4Cross-Modality Medical Image SegmentationImage Segmentation

    University of Science and Technology of China · Dresden University of Technology · Harbin Institute of Technology, Shenzhen

  25. HyDRA: A Hybrid Dual-Mode Network for Closed- and Open-Set RFFI with Optimized VMD

    Jul 16, 2025Hanwen Liu, Yuhe Huang, Yifeng Gong +2Hybrid CNN-Transformer ArchitecturesRF Fingerprint Identification

    School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen, 518107, China

  26. Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images

    Dec 3, 2024Xiangyong Lu, Masanori Suganuma, Takayuki OkataniHybrid CNN-Transformer ArchitecturesObject Pose Estimation

    Graduate School of Information Sciences, Tohoku University. · RIKEN Center for AIP

  27. Explainable Convolutional Neural Networks for Retinal Fundus Classification and Cutting-Edge Segmentation Models for Retinal Blood Vessels from Fundus Images

    May 12, 2024Fatema Tuj Johora Faria, Mukaffi Bin Moin, Pronay Debnath +2Explainable Medical Image AnalysisRetinal Vessel Segmentation

    aDepartment of Computer Science and Engineering, Ahsanullah University of Science and Technology, Dhaka, Bangladesh