Temporal Factorization of 3D Convolutional Kernels

12/09/2019
by   Gabrielle Ras, et al.
0

3D convolutional neural networks are difficult to train because they are parameter-expensive and data-hungry. To solve these problems we propose a simple technique for learning 3D convolutional kernels efficiently requiring less training data. We achieve this by factorizing the 3D kernel along the temporal dimension, reducing the number of parameters and making training from data more efficient. Additionally we introduce a novel dataset called Video-MNIST to demonstrate the performance of our method. Our method significantly outperforms the conventional 3D convolution in the low data regime (1 to 5 videos per class). Finally, our model achieves competitive results in the high data regime (>10 videos per class) using up to 45 parameters.

READ FULL TEXT
research
09/07/2019

Exploring Temporal Differences in 3D Convolutional Neural Networks

Traditional 3D convolutions are computationally expensive, memory intens...
research
01/26/2023

A Simple Algorithm For Scaling Up Kernel Methods

The recent discovery of the equivalence between infinitely wide neural n...
research
07/21/2022

Efficient CNN Architecture Design Guided by Visualization

Modern efficient Convolutional Neural Networks(CNNs) always use Depthwis...
research
01/19/2020

MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recogntion

To efficiently extract spatiotemporal features of video for action recog...
research
12/08/2016

Filter sharing: Efficient learning of parameters for volumetric convolutions

Typical convolutional neural networks (CNNs) have several millions of pa...
research
08/16/2023

KernelWarehouse: Towards Parameter-Efficient Dynamic Convolution

Dynamic convolution learns a linear mixture of n static kernels weighted...
research
09/29/2019

Learning Efficient Convolutional Networks through Irregular Convolutional Kernels

As deep neural networks are increasingly used in applications suited for...

Please sign up or login with your details

Forgot password? Click here to reset