Cyclic CNN: Image Classification With Multiscale and Multilocation Contexts

doi:10.1109/JIOT.2020.3038644

Cyclic CNN: Image Classification With Multiscale and Multilocation Contexts

2021-05-01

11

PRE

AI

DOI：10.1109/JIOT.2020.3038644

Original

Original request for help

Save

Abstract

En 中文

Improving the capability of models at limited computational cost is an urgent demand in many vision-based Internet-of-Things applications. Recent progress on deep convolutional neural network (CNN) has largely accelerated the development of image classification. Although the hierarchical structure of CNN naturally helps to extract image features in different scales and locations progressively, conventional convolution can only handle contexts of one scale and on a limited area of a single location in a specific layer, limiting the utilization of multiscale and multilocation information. In this work, we present a cyclic CNN framework, which enables sufficient utilization of multiscale and multilocation contexts in a single layer of convolution. The cyclic CNN is an extremely simple but effective improvement upon conventional convolution, which occupies no additional parameter and negligible computation (even less than 0.1%). Moreover, cyclic CNN can be easily plugged into many existing CNN pipelines, e.g., the ResNet family, obtaining extremely low-cost performance gain upon them. Extensive experiments on both small-scale (CIFAR10 and CIFAR100) and large-scale (ILSVRC2012) image classification benchmarks demonstrate that a consistent performance promotion is obtained with the help of cyclic CNN.

Keywords:

Convolution

Feature extraction

Task analysis

Internet of Things

Image resolution

Deep learning

Pipelines

Cyclic convolutional neural network (CNN)

image classification

multilocation contexts

multiscale contexts

Cyclic CNN: Image Classification With Multiscale and Multilocation Contexts

Abstract

AI Summary

Journal

Organization