mlsanityData to 14 Oct 2026

A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends

arXiv 2402.15490 ↗First posted 23 Feb 2024cs.LG cs.NEcited by 16

Not on the map. Why?

Abstract (arXiv)

In today's digital age, Convolutional Neural Networks (CNNs), a subset of Deep Learning (DL), are widely used for various computer vision tasks such as image classification, object detection, and image segmentation. There are numerous types of CNNs designed to meet specific needs and requirements, including 1D, 2D, and 3D CNNs, as well as dilated, grouped, attention, depthwise convolutions, and NAS, among others. Each type of CNN has its unique structure and characteristics, making it suitable for specific tasks. It's crucial to gain a thorough understanding and perform a comparative analysis of these different CNN types to understand their strengths and weaknesses. Furthermore, studying the performance, limitations, and practical applications of each type of CNN can aid in the development of new and improved architectures in the future. We also dive into the platforms and frameworks that researchers utilize for their research or development from various perspectives. Additionally, we explore the main research fields of CNN like 6D vision, generative models, and meta-learning. This survey paper provides a comprehensive examination and comparison of various CNN architectures, highlighting their architectural differences and emphasizing their respective advantages, disadvantages, applications, challenges, and future trends.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 150 of its 457 references that are in the map. First posted on arXiv 23 Feb 2024.

Builds on

150 of 457 references.

References · 150

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2017Mask R-CNNcited by 7,277
  7. 2016Densely Connected Convolutional Networkscited by 6,720
  8. 2022Generative Adversarial Networkscited by 5,627
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  10. 2014Going Deeper with Convolutionscited by 4,241
  11. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  12. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
38 more
  1. 2016Pyramid Scene Parsing Networkcited by 2,479
  2. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  3. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  4. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,553
  5. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  6. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,186
  7. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  8. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  9. 2017A Survey on Multi-Task Learningcited by 840
  10. 2014Deep Learning in Neural Networks: An Overviewcited by 770
  11. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 720
  12. 2020A Survey on Visual Transformercited by 654
  13. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  14. 2021Transformer in Transformercited by 633
  15. 2021ImageNet-21K Pretraining for the Massescited by 613
  16. 2018End-to-End Multi-Task Learning with Attentioncited by 534
  17. 2018Object Detection with Deep Learning: A Reviewcited by 528
  18. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  19. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
  20. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 470
  21. 2016Cross-stitch Networks for Multi-task Learningcited by 467
  22. 2017Deep Learning for Medical Image Analysiscited by 401
  23. 2020A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospectscited by 397
  24. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 292
  25. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  26. 2020Self-Supervised MultiModal Versatile Networkscited by 276
  27. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  28. 2020Neural Architecture Search without Trainingcited by 244
  29. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  30. 2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
  31. 2019CE-Net: Context Encoder Network for 2D Medical Image Segmentationcited by 220
  32. 2019A Survey of the Recent Architectures of Deep Convolutional Neural Networkscited by 213
  33. 2016Speed/accuracy trade-offs for modern convolutional object detectorscited by 198
  34. 2020U-Net and its variants for medical image segmentation: theory and applicationscited by 169
  35. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  36. 2022Pretraining is All You Need for Image-to-Image Translationcited by 160
  37. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 151
  38. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 148

50 most cited of 150 All 150 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 9; 2026: 3.

16 papers.

Sort:

By area:

  1. 2025Rethinking Multimodality: Optimizing Multimodal Deep Learning for Biomedical Signal Classificationcited by 7
  2. 2024On-Air Deep Learning Integrated Semantic Inference Models for Enhanced Earth Observation Satellite Networkscited by 4
  3. 2025QuFeX: Quantum feature extraction module for hybrid quantum-classical deep neural networkscited by 4
  4. 2025Are explainable AI (XAI) evaluation strategies aligned? Comparing subjective, objective, and mathematical evaluation measures using saliency mapscited by 4
  5. 2024Robust ADAS: Enhancing Robustness of Machine Learning-based Advanced Driver Assistance Systems for Adverse Weathercited by 2
  6. 2025DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classificationcited by 1
  7. 2025Image selective encryption analysis using mutual information in CNN based embedding spacecited by 1
  8. 2025PathMamba: A Hybrid Mamba-Transformer for Topologically Coherent Road Segmentation in Satellite Imagerycited by 1
  9. 2024A Mixture of Experts (MoE) model to improve AI-based computational pathology prediction performance under variable levels of histopathology image blurcited by 0
  10. 2024Advanced Hybrid Deep Learning Model for Enhanced Classification of Osteosarcoma Histopathology Imagescited by 0
  11. 2025Duo Streamers: A Streaming Gesture Recognition Frameworkcited by 0
  12. 2025Signal Intensity-weighted coordinate channels improve learning stability and generalisation in 1D and 2D CNNs in localisation tasks on biomedical signalscited by 0
4 more
  1. 2025GroupKAN: Efficient Kolmogorov-Arnold Networks via Grouped Spline Modelingcited by 0
  2. 2026GAFR-Net: A Graph Attention and Fuzzy-Rule Network for Interpretable Breast Cancer Image Classificationcited by 0
  3. 2026Scale-Gest: Scalable Model-Space Synthesis and Runtime Selection for On-Device Gesture Detectioncited by 0
  4. 2026Carry-Through Checksum: A Lightweight Fault-Detection for CNN Inference at the Edgecited by 0