DecomposeMe: Simplifying ConvNets for End-to-End Learning

06/17/2016
by   Jose Alvarez, et al.
0

Deep learning and convolutional neural networks (ConvNets) have been successfully applied to most relevant tasks in the computer vision community. However, these networks are computationally demanding and not suitable for embedded devices where memory and time consumption are relevant. In this paper, we propose DecomposeMe, a simple but effective technique to learn features using 1D convolutions. The proposed architecture enables both simplicity and filter sharing leading to increased learning capacity. A comprehensive set of large-scale experiments on ImageNet and Places2 demonstrates the ability of our method to improve performance while significantly reducing the number of parameters required. Notably, on Places2, we obtain an improvement in relative top-1 classification accuracy of 7.7% with an architecture that requires 92 proposed network is also demonstrated to generalize to other tasks by converting existing networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/05/2017

Relative Camera Pose Estimation Using Convolutional Neural Networks

This paper presents a convolutional neural network based approach for es...
research
07/25/2017

Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are well established models capable...
research
04/29/2021

Hardware Architecture of Embedded Inference Accelerator and Analysis of Algorithms for Depthwise and Large-Kernel Convolutions

In order to handle modern convolutional neural networks (CNNs) efficient...
research
01/19/2020

Towards More Efficient and Effective Inference: The Joint Decision of Multi-Participants

Existing approaches to improve the performances of convolutional neural ...
research
06/08/2015

Learning both Weights and Connections for Efficient Neural Networks

Neural networks are both computationally intensive and memory intensive,...
research
12/27/2021

A Multi-channel Training Method Boost the Performance

Deep convolutional neural network has made huge revolution and shown its...
research
11/09/2022

Cold Start Streaming Learning for Deep Networks

The ability to dynamically adapt neural networks to newly-available data...

Please sign up or login with your details

Forgot password? Click here to reset