arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1711.09280cs.CV
收藏

用于大规模图像识别的渐进更新神经网络

Gradually Updated Neural Networks for Large-Scale Image Recognition

Johns Hopkins University(约翰霍普金斯大学);Shanghai University(上海大学);Hikvision Research(海康威视研究(Hikvision Research))

Siyuan Qiao, Zhishuai Zhang, Wei Shen, Bo Wang, Alan Yuille

摘要:

深度是神经网络在大规模图像识别中取得成功的关键之一。最先进的网络架构通常通过级联卷积层或构建块来增加深度。在本文中,我们提出了一种替代方法来增加深度。我们的方法是通过将计算排序引入卷积层或块内的通道,基于此,我们以通道方式逐渐计算输出。增加的排序不仅增加了网络的深度和学习能力,而没有任何额外的计算成本,而且还消除了重叠奇点,使网络能够更快地收敛,性能更好。实验表明,基于我们的方法的网络达到了最先进的性能CIFAR和ImageNet数据集。

英文摘要:

Depth is one of the keys that make neural networks succeed in the task of large-scale image recognition. The state-of-the-art network architectures usually increase the depths by cascading convolutional layers or building blocks. In this paper, we present an alternative method to increase the depth. Our method is by introducing computation orderings to the channels within convolutional layers or blocks, based on which we gradually compute the outputs in a channel-wise manner. The added orderings not only increase the depths and the learning capacities of the networks without any additional computation costs, but also eliminate the overlap singularities so that the networks are able to converge faster and perform better. Experiments show that the networks based on our method achieve the state-of-the-art performances on CIFAR and ImageNet datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑