mlsanityData to 14 Oct 2026

Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey

arXiv 2402.02941 ↗First posted 5 Feb 2024cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

The hybrid of Convolutional Neural Network (CNN) and Vision Transformers (ViT) architectures has emerged as a groundbreaking approach, pushing the boundaries of computer vision (CV). This comprehensive review provides a thorough examination of the literature on state-of-the-art hybrid CNN-ViT architectures, exploring the synergies between these two approaches. The main content of this survey includes: (1) a background on the vanilla CNN and ViT, (2) systematic review of various taxonomic hybrid designs to explore the synergy achieved through merging CNNs and ViTs models, (3) comparative analysis and application task-specific synergy between different hybrid architectures, (4) challenges and future directions for hybrid models, (5) lastly, the survey concludes with a summary of key findings and recommendations. Through this exploration of hybrid CV architectures, the survey aims to serve as a guiding resource, fostering a deeper understanding of the intricate dynamics between CNNs and ViTs and their collective impact on shaping the future of CV architectures.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 81 of its 128 references that are in the map. First posted on arXiv 5 Feb 2024.

Builds on

81 of 128 references.

References · 81

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2017Mask R-CNNcited by 7,277
  8. 2016Densely Connected Convolutional Networkscited by 6,720
  9. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  10. 2017Squeeze-and-Excitation Networkscited by 4,789
  11. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  12. 2014Going Deeper with Convolutionscited by 4,241
38 more
  1. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  2. 2020Longformer: The Long-Document Transformercited by 3,413
  3. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  4. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  5. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  6. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  7. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  8. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  9. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  10. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,068
  11. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  12. 2021Transformers in Vision: A Surveycited by 1,013
  13. 2018Dual Attention Network for Scene Segmentationcited by 1,003
  14. 2021Scaling Vision Transformerscited by 999
  15. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  16. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  17. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  18. 2018Image Transformercited by 772
  19. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 675
  20. 2020A Survey on Visual Transformercited by 654
  21. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  22. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 575
  23. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 569
  24. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 518
  25. 2017Progressive Neural Architecture Searchcited by 487
  26. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  27. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
  28. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  29. 2021Nystr"omformer: A Nystr"om-Based Algorithm for Approximating Self-Attentioncited by 471
  30. 2021A Survey of Transformerscited by 401
  31. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  32. 2019Multi-Label Image Recognition with Graph Convolutional Networkscited by 322
  33. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
  34. 2020Exploring Self-attention for Image Recognitioncited by 313
  35. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  36. 2019Adversarial Examples Improve Image Recognitioncited by 286
  37. 2017Temporal Segment Networks for Action Recognition in Videoscited by 279
  38. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 241

50 most cited of 81 All 81 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 6; 2026: 2.

13 papers.

Sort:

By area:

  1. 2025Hypergraph Vision Transformers: Images are More than Nodes, More than Edgescited by 16
  2. 2024Convolutional Neural Networks and Vision Transformers for Fashion MNIST Classification: A Literature Reviewcited by 2
  3. 2025An Attention-Guided Deep Learning Approach for Classifying 39 Skin Lesion Typescited by 1
  4. 2025A Retrospective Systematic Study on Hierarchical Sparse Query Transformer-assisted Ultrasound Screening for Early Hepatocellular Carcinomacited by 1
  5. 2024Dual sparse training framework: inducing activation map sparsity via Transformed ℓ1 regularizationcited by 0
  6. 2024iiANET: Inception Inspired Attention Hybrid Network for efficient Long-Range Dependencycited by 0
  7. 2024KonvLiNA: Integrating Kolmogorov-Arnold Network with Linear Nystr"om Attention for feature fusion in Crop Field Detectioncited by 0
  8. 2024Data-driven tool wear prediction in milling, based on a process-integrated single-sensor approachcited by 0
  9. 2025DFYP: A Dynamic Fusion Framework with Spectral Channel Attention and Adaptive Operator learning for Crop Yield Predictioncited by 0
  10. 2025CNN-ViT Hybrid for Pneumonia Detection: Theory and Empiric on Limited Data without Pretrainingcited by 0
  11. 2025MedCondDiff: Lightweight, Robust, Semantically Guided Diffusion for Medical Image Segmentationcited by 0
  12. 2026Federated Vision Transformer with Adaptive Focal Loss for Medical Image Classificationcited by 0
1 more
  1. 2026Enhancing Shrimp Disease Detection via Deep Learning and Data Refinement for Resilient Aquaculturecited by 0