Should You Go Deeper? Optimizing Convolutional Neural Network Architectures without Training by Receptive Field Analysis

06/23/2021
by   Mats L. Richter, et al.
0

Applying artificial neural networks (ANN) to specific tasks, researchers, programmers, and other specialists usually overshot the number of convolutional layers in their designs. By implication, these ANNs hold too many parameters, which needed unnecessarily trained without impacting the result. The features, a convolutional layer can process, are strictly limited by its receptive field. By layer-wise analyzing the expansion of the receptive fields, we can reliably predict sequences of layers that will not contribute qualitatively to the inference in thegiven ANN architecture. Based on these analyses, we propose design strategies to resolve these inefficiencies, optimizing the explainability and the computational performance of ANNs. Since neither the strategies nor the analysis requires training of the actual model, these insights allow for a very efficient design process of ANNs architectures which might be automated in the future.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/19/2017

What are the Receptive, Effective Receptive, and Projective Fields of Neurons in Convolutional Neural Networks?

In this work, we explain in detail how receptive fields, effective recep...
research
11/26/2022

Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance

Minimal changes to neural architectures (e.g. changing a single hyperpar...
research
11/11/2017

Learning Document Embeddings With CNNs

We propose a new model for unsupervised document embedding. Existing app...
research
07/09/2021

DDCNet: Deep Dilated Convolutional Neural Network for Dense Prediction

Dense pixel matching problems such as optical flow and disparity estimat...
research
11/14/2019

Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling

Convolutional neural networks (CNNs) with dilated filters such as the Wa...
research
11/20/2018

Multi-scale aggregation of phase information for reducing computational cost of CNN based DOA estimation

In a recent work on direction-of-arrival (DOA) estimation of multiple sp...

Please sign up or login with your details

Forgot password? Click here to reset