mlsanityData to 7 Oct 2026

Deep Convolutional Neural Networks with Zero-Padding: Feature Extraction and Learning

arXiv 2307.16203 ↗First posted 30 Jul 2023cs.LG cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

This paper studies the performance of deep convolutional neural networks (DCNNs) with zero-padding in feature extraction and learning. After verifying the roles of zero-padding in enabling translation-equivalence, and pooling in its translation-invariance driven nature, we show that with similar number of free parameters, any deep fully connected networks (DFCNs) can be represented by DCNNs with zero-padding. This demonstrates that DCNNs with zero-padding is essentially better than DFCNs in feature extraction. Consequently, we derive universal consistency of DCNNs with zero-padding and show its translation-invariance in the learning process. All our theoretical results are verified by numerical experiments including both toy simulations and real-data running.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 19 of its 36 references that are in the map. First posted on arXiv 30 Jul 2023.

Builds on

19 of 36 references.

References · 19

  1. 2016Error bounds for approximations with deep ReLU networkscited by 567
  2. 2017Nonparametric regression using deep neural networks with ReLU activation functioncited by 431
  3. 2015Recent Advances in Convolutional Neural Networkscited by 360
  4. 2017Optimal approximation of piecewise smooth functions using deep ReLU neural networkscited by 176
  5. 2018Universality of Deep Convolutional Neural Networkscited by 176
  6. 2020On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Locationcited by 141
  7. 2017Approximating Continuous Functions by ReLU Nets of Minimal Widthcited by 120
  8. 2016Why does deep and cheap learning work so well?cited by 100
  9. 2019Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 80
  10. 2016Deep vs. shallow networks : An approximation theory perspectivecited by 63
  11. 2015Provable approximation properties for deep neural networkscited by 60
  12. 2016Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networkscited by 58
7 more
  1. 2019Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networkscited by 40
  2. 2018Equivalence of approximation by convolutional neural networks and fully-connected networkscited by 38
  3. 2021Universal Consistency of Deep Convolutional Neural Networkscited by 16
  4. 2020Depth Selection for Deep ReLU Nets in Feature Extraction and Generalizationcited by 13
  5. 2018Generalization and Expressivity for Deep Netscited by 11
  6. 2019Deep Neural Networks for Rotation-Invariance Approximation and Learningcited by 10
  7. 2019Realization of spatial sparseness by deep ReLU nets with massive datacited by 10

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 2.

4 papers.

  1. 2025Two-Dimensional Deep ReLU CNN Approximation for Korobov Functions: A Constructive Approachcited by 2
  2. 2023Optimal Approximation and Learning Rates for Deep Convolutional Neural Networkscited by 1
  3. 2024Component-based Sketching for Deep ReLU Netscited by 1
  4. 2025Feature Qualification by Deep Nets: A Constructive Approachcited by 0