paper-with-me

Papers

Computational optimization of convolutional neural networks using separated filters architecture

2020-02-18 · Elena Limonova, Alexander Sheshkus, Dmitry Nikolaev

This paper considers a convolutional neural network transformation that reduces computation complexity and thus speedups neural network processing. Usage of convolutional neural networks (CNN) is the standard approach to image recognition despite the fact they can be too computationally demanding, for example for recognition on mobile platforms or in embedded systems. In this paper we propose CNN structure transformation which expresses 2D convolution filters as a linear combination of separable filters. It allows to obtain separated convolutional filters by standard training algorithms. We study the computation efficiency of this structure transformation and suggest fast implementation easily handled by CPU or GPU. We demonstrate that CNNs designed for letter and digit recognition of proposed structure show 15% speedup without accuracy loss in industrial image recognition system. In conclusion, we discuss the question of possible accuracy decrease and the application of proposed transformation to different recognition problems. convolutional neural networks, computational optimization, separable filters, complexity reduction.

📄 PDF Abstract BibTeX arXiv:2002.07754

Code (0)

등록된 구현이 없습니다.

Tasks

CPUGPU

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

3D Dense Separated Convolution Module for Volumetric Image Analysis

2019-05-14 · Lei Qu, Changfeng Wu, Liang Zou

With the thriving of deep learning, 3D Convolutional Neural Networks have become a popular choice in volumetric image analysis due to their impressive 3D contexts mining ability. However, the 3D convolutional kernels wil…

image-classificationImage Classification

Video Classification with Channel-Separated Convolutional Networks

2019-04-04 · ICCV 2019 10 · Du Tran, Heng Wang, Lorenzo Torresani, Matt Feiszli

Group convolution has been shown to offer great computational savings in various 2D convolutional architectures for image classification. It is natural to ask: 1) if group convolution can help to alleviate the high compu…

Action ClassificationAction RecognitionGeneral Classificationimage-classification+2

Approximated Oracle Filter Pruning for Destructive CNN Width Optimization

2019-05-12 · Xiaohan Ding, Guiguang Ding, Yuchen Guo, Jungong Han 외

It is not easy to design and run Convolutional Neural Networks (CNNs) due to: 1) finding the optimal number of filters (i.e., the width) at each layer is tricky, given an architecture; and 2) the computational intensity …

Reliable Deep Learning Plant Leaf Disease Classification Based on Light-Chroma Separated Branches

2021-10-14 · 23rd International Conference of the Catalan Association for Artificial Intelligence 2021 10 · Joao Paulo Schwarz Schuler, Santiago Romani, Mohamed Abdel-Nasser, Hatem Rashwan 외

The Food and Agriculture Organization (FAO) estimated that plant diseases cost the world economy $220 billion in 2019. In this paper, we propose a lightweight Deep Convolutional Neural Network (DCNN) for automatic and re…

Image Classification

On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment

2025-07-09 · Sarah Ball, Greg Gluch, Shafi Goldwasser, Frauke Kreuter 외 arxiv

With the increased deployment of large language models (LLMs), one concern is their potential misuse for generating harmful content. Our work studies the alignment challenge, with a focus on filters to prevent the genera…