ResNeXt算法的简介(论文介绍)
ResNeXt算法是由Facebook研究人员提出,当时何凯明(ResNet算法作者之一)已经在Facebook工作了,
Abstract
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 .
摘要
我们提出了一种简单、高度模块化的图像分类网络结构。我们的网络是通过重复一个构建块来构建的,这个构建块聚合了一组具有相同拓扑结构的转换。我们的简单设计了一个同质的多分支体系结构,只需要设置几个超参数。这个策略公开了一个新的维度,我们称之为“基数”(转换集的大小),它是除深度和宽度维度之外的一个基本因素。在 ImageNet-1K数据集上,我们通过经验证明,即使在保持复杂度的限制条件下,增加基数也能提高分类精度。此外,当我们增加容量时,增加基数比更深入或更广泛更有效。我们的模型名为ResNeXt,是我们进入ILSVRC 2016分类任务的基础,在该任务中我们获得了第二名。我们进一步研究了 ImageNet-5K集和 COCO检测集上的ResNet,也显示出比ResNet对应的更好的结果。代码和模型在网上公开。
论文
Saining Xie, Ross Girshick, Piotr Dollár, ZhuowenTu, and KaimingHe.
Aggregated residual transformations for deep neural networks. CVPR 2017
https://arxiv.org/abs/1611.05431
ResNeXt算法的架构详解
DL之ResNeXt:ResNeXt算法的架构详解
https://yunyaniu.blog.csdn.net/article/details/98103063
ResNeXt算法的案例应用
更新……