paper-with-me

Papers

Padding-free Convolution based on Preservation of Differential Characteristics of Kernels

2023-09-12 · Kuangdai Leng, Jeyan Thiyagalingam

Convolution is a fundamental operation in image processing and machine learning. Aimed primarily at maintaining image size, padding is a key ingredient of convolution, which, however, can introduce undesirable boundary effects. We present a non-padding-based method for size-keeping convolution based on the preservation of differential characteristics of kernels. The main idea is to make convolution over an incomplete sliding window "collapse" to a linear differential operator evaluated locally at its central pixel, which no longer requires information from the neighbouring missing pixels. While the underlying theory is rigorous, our final formula turns out to be simple: the convolution over an incomplete window is achieved by convolving its nearest complete window with a transformed kernel. This formula is computationally lightweight, involving neither interpolation or extrapolation nor restrictions on image and kernel sizes. Our method favours data with smooth boundaries, such as high-resolution images and fields from physics. Our experiments include: i) filtering analytical and non-analytical fields from computational physics and, ii) training convolutional neural networks (CNNs) for the tasks of image classification, semantic segmentation and super-resolution reconstruction. In all these experiments, our method has exhibited visible superiority over the compared ones.

📄 PDF Abstract BibTeX arXiv:2309.06370

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage ClassificationSemantic SegmentationSuper-Resolution

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

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 po…

Translation

Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features

2022-06-02 · Chieh Hubert Lin, Hsin-Ying Lee, Hung-Yu Tseng, Maneesh Singh 외

Recent studies show that paddings in convolutional neural networks encode absolute position information which can negatively affect the model performance for certain tasks. However, existing metrics for quantifying the s…

Position

Random Padding Data Augmentation

2023-02-17 · Nan Yang, Laicheng Zhong, Fan Huang, Dong Yuan 외

The convolutional neural network (CNN) learns the same object in different positions in images, which can improve the recognition accuracy of the model. An implication of this is that CNN may know where the object is. Th…

Data Augmentationimage-classificationImage ClassificationPosition

Partial Convolution based Padding

2018-11-28 · Guilin Liu, Kevin J. Shih, Ting-Chun Wang, Fitsum A. Reda 외

In this paper, we present a simple yet effective padding scheme that can be used as a drop-in module for existing convolutional neural networks. We call it partial convolution based padding, with the intuition that the p…

General ClassificationSemantic 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