arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1507.08754cs.CV
收藏

图像分类卷积神经网络的翻转旋转池卷积和分裂丢弃

Flip-Rotate-Pooling Convolution and Split Dropout on Convolution Neural Networks for Image Classification

Zhejiang University(浙江大学)

Fa Wu, Peijun Hu, Dexing Kong

摘要:

本文提出了一种新版本的Dropout,称为Split Dropout(sDropout)和旋转卷积技术,以提高CNN在图像分类上的性能。广泛使用的标准Dropout具有通过在训练期间随机丢弃单元来防止深度神经网络过拟合的优点。我们的sDropout将数据随机分为两个子集,并保留两个子集,而不是丢弃一个子集。我们还介绍了两种旋转卷积技术,即旋转池卷积(RPC)和翻转旋转池卷积(FRPC),以提高CNN在旋转变换鲁棒性方面的性能。这两种技术将旋转不变性编码到网络中,而无需添加额外的参数。在ImageNet 2012分类任务上的实验结果表明,sDropout不仅提高了性能,而且收敛速度更快。此外,RPC和FRPC使CNN在旋转变换方面更加健壮。总的来说,与原始网络相比,FRPC与sDropout一起在ImageNet 2012分类任务中带来了$1.18\%$(Zeiler和Fergus的模型~ \cite{zeiler2013visualizing},10-view,top-1)的准确性提高。

英文摘要:

This paper presents a new version of Dropout called Split Dropout (sDropout) and rotational convolution techniques to improve CNNs' performance on image classification. The widely used standard Dropout has advantage of preventing deep neural networks from overfitting by randomly dropping units during training. Our sDropout randomly splits the data into two subsets and keeps both rather than discards one subset. We also introduce two rotational convolution techniques, i.e. rotate-pooling convolution (RPC) and flip-rotate-pooling convolution (FRPC) to boost CNNs' performance on the robustness for rotation transformation. These two techniques encode rotation invariance into the network without adding extra parameters. Experimental evaluations on ImageNet2012 classification task demonstrate that sDropout not only enhances the performance but also converges faster. Additionally, RPC and FRPC make CNNs more robust for rotation transformations. Overall, FRPC together with sDropout bring $1.18\%$ (model of Zeiler and Fergus~\cite{zeiler2013visualizing}, 10-view, top-1) accuracy increase in ImageNet 2012 classification task compared to the original network.

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。

↑