mlsanityData to 14 Oct 2026

A guide to convolution arithmetic for deep learning

arXiv 1603.07285 ↗First posted 23 Mar 2016stat.ML cs.LG cs.NEcited by 185

Not on the map. Why?

Abstract (arXiv)

We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, zero padding, strides and output shape) of convolutional, pooling and transposed convolutional layers, as well as the relationship between convolutional and transposed convolutional layers. Relationships are derived for various cases, and are illustrated in order to make them intuitive.

Key facts. Cited by 185 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 43; 2022: 34; 2023: 34; 2024: 32; 2025: 29; 2026: 12.

185 papers.

Sort:

By area:

  1. 2022Generative Adversarial Networkscited by 5,627
  2. 2021NeRV: Neural Representations for Videoscited by 256
  3. 2022SimVP: Simpler yet Better Video Predictioncited by 184
  4. 2024FeatUp: A Model-Agnostic Framework for Features at Any Resolutioncited by 116
  5. 2021Dive into Deep Learningcited by 111
  6. 2021Exploiting Explanations for Model Inversion Attackscited by 49
  7. 2023Fully Hyperbolic Convolutional Neural Networks for Computer Visioncited by 49
  8. 2023PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Predictioncited by 44
  9. 2022Machine Learning in Aerodynamic Shape Optimizationcited by 39
  10. 2021Hierarchical Associative Memorycited by 34
  11. 2021Eformer: Edge Enhancement based Transformer for Medical Image Denoisingcited by 30
  12. 2021Unsupervised Object Learning via Common Fatecited by 29
38 more
  1. 2024RiemannONets: Interpretable Neural Operators for Riemann Problemscited by 28
  2. 2021Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Networkcited by 26
  3. 2021Generative Modeling of Turbulencecited by 26
  4. 2023A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRUcited by 25
  5. 2023Rethinking materials simulations: Blending direct numerical simulations with neural operatorscited by 25
  6. 2025LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Modelscited by 23
  7. 2021Joint Progressive and Coarse-to-fine Registration of Brain MRI via Deformation Field Integration and Non-Rigid Feature Fusioncited by 22
  8. 2021A Comparison of Neural Network Architectures for Data-Driven Reduced-Order Modelingcited by 22
  9. 2023FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Visioncited by 22
  10. 2022KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolutioncited by 18
  11. 2022Unsupervised Structure-Texture Separation Network for Oracle Character Recognitioncited by 15
  12. 2021Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Functioncited by 11
  13. 2023Certified Zeroth-order Black-Box Defense with Robust UNet Denoisercited by 11
  14. 2023Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation using Compact Implicit Layerscited by 11
  15. 2024Hierarchical Neural Operator Transformer with Learnable Frequency-aware Loss Prior for Arbitrary-scale Super-resolutioncited by 11
  16. 2025Parameter-Efficient Fine-Tuning of Large Language Models via Deconvolution in Subspacecited by 11
  17. 2021Towards a Computed-Aided Diagnosis System in Colonoscopy: Automatic Polyp Segmentation Using Convolution Neural Networkscited by 10
  18. 2021Learning A 3D-CNN and Transformer Prior for Hyperspectral Image Super-Resolutioncited by 10
  19. 2021Detection of Deepfake Videos Using Long Distance Attentioncited by 9
  20. 2022Low Complexity Channel estimation with Neural Network Solutionscited by 9
  21. 2022Less is More: Proxy Datasets in NAS approachescited by 9
  22. 2023Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Contextcited by 8
  23. 2023Fast, Interpretable, and Deterministic Time Series Classification With a Bag-of-Receptive-Fieldscited by 8
  24. 2024Lipschitz constant estimation for general neural network architectures using control toolscited by 8
  25. 2025Blurred Encoding for Trajectory Representation Learningcited by 8
  26. 2021Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systemscited by 7
  27. 2022Simpler is better: spectral regularization and up-sampling techniques for variational autoencoderscited by 7
  28. 2022A Bayesian Deep Learning Approach to Near-Term Climate Predictioncited by 7
  29. 2023Breaching FedMD: Image Recovery via Paired-Logits Inversion Attackcited by 7
  30. 2024Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Spacecited by 7
  31. 2025FedConv: A Learning-on-Model Paradigm for Heterogeneous Federated Clientscited by 7
  32. 2021A Competitive Edge: Can FPGAs Beat GPUs at DCNN Inference Acceleration in Resource-Limited Edge Computing Applications?cited by 6
  33. 2021Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstructioncited by 6
  34. 2025FeatSharp: Your Vision Model Features, Sharpercited by 6
  35. 2019State Representation Learning from Demonstrationcited by 5
  36. 2022DSLA: Dynamic smooth label assignment for efficient anchor-free object detectioncited by 5
  37. 2022A Continuous Convolutional Trainable Filter for Modelling Unstructured Datacited by 5
  38. 2024Text-to-Image Cross-Modal Generation: A Systematic Reviewcited by 5

50 most cited of 185 All 185 (JSON)