paper-with-me

Papers

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

2023-07-30 · Zhi Han, Baichen Liu, Shao-Bo Lin, Ding-Xuan Zhou

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.

📄 PDF Abstract BibTeX arXiv:2307.16203

Code (1)

liubc17/eDCNN_zero_padding 공식 구현 tf

Tasks

Translation

Similar Papers 제목 키워드 기반

Improving Translation Invariance in Convolutional Neural Networks with Peripheral Prediction Padding

2023-07-15 · Kensuke Mukai, Takao Yamanaka

Zero padding is often used in convolutional neural networks to prevent the feature map size from decreasing with each layer. However, recent studies have shown that zero padding promotes encoding of absolute positional i…

Semantic SegmentationTranslation

Context-aware Padding for Semantic Segmentation

2021-09-16 · Yu-Hui Huang, Marc Proesmans, Luc van Gool

Zero padding is widely used in convolutional neural networks to prevent the size of feature maps diminishing too fast. However, it has been claimed to disturb the statistics at the border. As an alternative, we propose a…

SegmentationSemantic Segmentation

On the Interplay of Convolutional Padding and Adversarial Robustness

2023-08-12 · Paul Gavrikov, Janis Keuper

It is common practice to apply padding prior to convolution operations to preserve the resolution of feature-maps in Convolutional Neural Networks (CNN). While many alternatives exist, this is often achieved by adding a …

Adversarial Robustness

Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks

2021-08-16 · ICCV 2021 10 · Yu-Qi Yang, Peng-Shuai Wang, Yang Liu

Sparse voxel-based 3D convolutional neural networks (CNNs) are widely used for various 3D vision tasks. Sparse voxel-based 3D CNNs create sparse non-empty voxels from the 3D input and perform 3D convolution operations on…

SegmentationSemantic Segmentation

Spectral Norm of Convolutional Layers with Circular and Zero Paddings

2024-01-31 · Blaise Delattre, Quentin Barthélemy, Alexandre Allauzen

This paper leverages the use of \emph{Gram iteration} an efficient, deterministic, and differentiable method for computing spectral norm with an upper bound guarantee. Designed for circular convolutional layers, we gener…