paper-with-me

Papers

Reduce Computational Complexity for Convolutional Layers by Skipping Zeros

2023-06-28 · Zhiyi Zhang, Pengfei Zhang, Zhuopin Xu, Qi Wang

Convolutional neural networks necessitate good algorithms to reduce complexity, and sufficient utilization of parallel processors for acceleration. Within convolutional layers, there are three types of operators: convolution used in forward propagation, deconvolution and dilated-convolution utilized in backward propagation. During the execution of these operators, zeros are typically added to tensors, leading to redundant calculations and unnecessary strain on hardware. To circumvent these inefficiencies, we propose the C-K-S algorithm, accompanied by efficient GPU implementations. C-K-S trims filters to exclude zero-padding. For deconvolution and dilated-convolution, C-K-S transforms sparse tensors into dense tensors, and standardizes the local computational rules to simplify the hardware control. The experimental results demonstrate that C-K-S offers good performance in terms of speed and convergence, surpassing the capabilities of PyTorch and cuDNN in certain scenarios.

📄 PDF Abstract BibTeX arXiv:2306.15951

Code (0)

등록된 구현이 없습니다.

Tasks

GPU

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
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

Optimization of Layer Skipping and Frequency Scaling for Convolutional Neural Networks under Latency Constraint

2025-03-31 · Minh David Thao Chan, Ruoyu Zhao, Yukuan Jia, Ruiqing Mao 외

The energy consumption of Convolutional Neural Networks (CNNs) is a critical factor in deploying deep learning models on resource-limited equipment such as mobile devices and autonomous vehicles. We propose an approach i…

Autonomous VehiclesComputational Efficiency

Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models

2024-07-22 · Georgy Tyukin, Gbetondji J-S Dovonon, Jean Kaddour, Pasquale Minervini

The inference demand for LLMs has skyrocketed in recent months, and serving models with low latencies remains challenging due to the quadratic input length complexity of the attention layers. In this work, we investigate…

All

PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions

2015-04-30 · NeurIPS 2016 12 · Michael Figurnov, Aijan Ibraimova, Dmitry Vetrov, Pushmeet Kohli

We propose a novel approach to reduce the computational cost of evaluation of convolutional neural networks, a factor that has hindered their deployment in low-power devices such as mobile phones. Inspired by the loop pe…

SkipNet: Learning Dynamic Routing in Convolutional Networks

2017-11-26 · ECCV 2018 9 · Xin Wang, Fisher Yu, Zi-Yi Dou, Trevor Darrell 외

While deeper convolutional networks are needed to achieve maximum accuracy in visual perception tasks, for many inputs shallower networks are sufficient. We exploit this observation by learning to skip convolutional laye…

Decision MakingReinforcement LearningSequential Decision Making

SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model

2024-10-04 · Grzegorz Stefański, Paweł Daniluk, Artur Szumaczuk, Jakub Tkaczuk

Consumer electronics used to follow the miniaturization trend described by Moore's Law. Despite increased processing power in Microcontroller Units (MCUs), MCUs used in the smallest appliances are still not capable of ru…

Time Series