基数(数据建模)
计算机科学
集合(抽象数据类型)
简单(哲学)
维数(图论)
块(置换群论)
人工神经网络
残余物
理论计算机科学
编码(集合论)
建筑
同种类的
人工智能
机器学习
算法
数据挖掘
数学
程序设计语言
组合数学
视觉艺术
艺术
哲学
认识论
作者
Saining Xie,Ross Girshick,Piotr Dollár,Zhuowen Tu,Kaiming He
出处
期刊:Computer Vision and Pattern Recognition
日期:2017-07-01
被引量:9177
标识
DOI:10.1109/cvpr.2017.634
摘要
We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set. This strategy exposes a new dimension, which we call cardinality (the size of the set of transformations), as an essential factor in addition to the dimensions of depth and width. On the ImageNet-1K dataset, we empirically show that even under the restricted condition of maintaining complexity, increasing cardinality is able to improve classification accuracy. Moreover, increasing cardinality is more effective than going deeper or wider when we increase the capacity. Our models, named ResNeXt, are the foundations of our entry to the ILSVRC 2016 classification task in which we secured 2nd place. We further investigate ResNeXt on an ImageNet-5K set and the COCO detection set, also showing better results than its ResNet counterpart. The code and models are publicly available online.
科研通智能强力驱动
Strongly Powered by AbleSci AI