RecNets: Channel-wise Recurrent Convolutional Neural Networks

05/28/2019
by   George Retsinas, et al.
0

In this paper, we introduce Channel-wise recurrent convolutional neural networks (RecNets), a family of novel, compact neural network architectures for computer vision tasks inspired by recurrent neural networks (RNNs). RecNets build upon Channel-wise recurrent convolutional (CRC) layers, a novel type of convolutional layer that splits the input channels into disjoint segments and processes them in a recurrent fashion. In this way, we simulate wide, yet compact models, since the number of parameters is vastly reduced via the parameter sharing of the RNN formulation. Experimental results on the CIFAR-10 and CIFAR-100 image classification tasks demonstrate the superior size-accuracy trade-off of RecNets compared to other compact state-of-the-art architectures.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/14/2018

Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures

We characterize convolutional neural networks with respect to the relati...
research
02/26/2019

Learning Implicitly Recurrent CNNs Through Parameter Sharing

We introduce a parameter sharing scheme, in which different layers of a ...
research
08/25/2023

Squeeze aggregated excitation network

Convolutional neural networks have spatial representations which read pa...
research
10/21/2017

Incomplete Dot Products for Dynamic Computation Scaling in Neural Network Inference

We propose the use of incomplete dot products (IDP) to dynamically adjus...
research
07/31/2017

Analysis and Optimization of Convolutional Neural Network Architectures

Convolutional Neural Networks (CNNs) dominate various computer vision ta...
research
02/23/2021

Arguments for the Unsuitability of Convolutional Neural Networks for Non–Local Tasks

Convolutional neural networks have established themselves over the past ...
research
11/10/2022

MGiaD: Multigrid in all dimensions. Efficiency and robustness by coarsening in resolution and channel dimensions

Current state-of-the-art deep neural networks for image classification a...

Please sign up or login with your details

Forgot password? Click here to reset