Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks

10/29/2018
by   Jie Hu, et al.
0

While the use of bottom-up local operators in convolutional neural networks (CNNs) matches well some of the statistics of natural images, it may also prevent such models from capturing contextual long-range feature interactions. In this work, we propose a simple, lightweight approach for better context exploitation in CNNs. We do so by introducing a pair of operators: gather, which efficiently aggregates feature responses from a large spatial extent, and excite, which redistributes the pooled information to local features. The operators are cheap, both in terms of number of added parameters and computational complexity, and can be integrated directly in existing architectures to improve their performance. Experiments on several datasets show that gather-excite can bring benefits comparable to increasing the depth of a CNN at a fraction of the cost. For example, we find ResNet-50 with gather-excite operators is able to outperform its 101-layer counterpart on ImageNet with no additional learnable parameters. We also propose a parametric gather-excite operator pair which yields further performance gains, relate it to the recently-introduced Squeeze-and-Excitation Networks, and analyse the effects of these changes to the CNN feature activation statistics.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/15/2019

LeanResNet: A Low-cost yet Effective Convolutional Residual Networks

Convolutional Neural Networks (CNNs) filter the input data using a serie...
research
05/20/2018

Low-Cost Parameterizations of Deep Convolutional Neural Networks

Convolutional Neural Networks (CNNs) filter the input data using a serie...
research
10/29/2019

LeanConvNets: Low-cost Yet Effective Convolutional Neural Networks

Convolutional Neural Networks (CNNs) have become indispensable for solvi...
research
04/02/2023

Resolution-Invariant Image Classification based on Fourier Neural Operators

In this paper we investigate the use of Fourier Neural Operators (FNOs) ...
research
07/24/2023

Learnable wavelet neural networks for cosmological inference

Convolutional neural networks (CNNs) have been shown to both extract mor...
research
06/12/2019

DeepSquare: Boosting the Learning Power of Deep Convolutional Neural Networks with Elementwise Square Operators

Modern neural network modules which can significantly enhance the learni...
research
04/28/2020

3D Solid Spherical Bispectrum CNNs for Biomedical Texture Analysis

Locally Rotation Invariant (LRI) operators have shown great potential in...

Please sign up or login with your details

Forgot password? Click here to reset