arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1807.01418cs.CVcs.NE
收藏

用于低成本失真图像分类的选择性深度卷积神经网络

Selective Deep Convolutional Neural Network for Low Cost Distorted Image Classification

Minho Ha, Younghoon Byeon, Youngjoo Lee, Sunggu Lee

摘要:

深度卷积神经网络已被证明非常适合图像分类应用。然而,如果图像中存在失真,则即使使用最先进的神经网络,分类精度也会显著降低。通过简单地使用失真图像进行训练,无法显著提高准确性。相反,本文提出了一种多神经网络拓扑结构,称为选择性深度卷积神经网络。通过以所提出的方式修改现有的最先进的神经网络,示出了可以实现类似水平的分类精度,但是以显著更低的成本。成本降低主要是通过使用较少的权重参数来实现的。使用更少的权重减少了乘法-累加运算的数量,并且还减少了数据访问所需的能量。最后,它表明,所提出的选择性深度卷积神经网络的有效性,可以进一步提高它与以前提出的网络成本降低方法相结合。

英文摘要:

Deep convolutional neural networks have proven to be well suited for image classification applications. However, if there is distortion in the image, the classification accuracy can be significantly degraded, even with state-of-the-art neural networks. The accuracy cannot be significantly improved by simply training with distorted images. Instead, this paper proposes a multiple neural network topology referred to as a selective deep convolutional neural network. By modifying existing state-of-the-art neural networks in the proposed manner, it is shown that a similar level of classification accuracy can be achieved, but at a significantly lower cost. The cost reduction is obtained primarily through the use of fewer weight parameters. Using fewer weights reduces the number of multiply-accumulate operations and also reduces the energy required for data accesses. Finally, it is shown that the effectiveness of the proposed selective deep convolutional neural network can be further improved by combining it with previously proposed network cost reduction methods.

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。

↑