ICNN: An iterative implementation of convolutional neural networks to enable energy and computational complexity aware dynamic approximation
ICNN: An iterative implementation of convolutional neural networks to enable energy and computational complexity aware dynamic approximation
复制标题
DOI：
10.23919/date.2018.8342068
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
Katayoun Neshatpour;F. Behnia;H. Homayoun;Avesta Sasan
中科院分区：
文献类型：
--
作者：
Katayoun Neshatpour;F. Behnia;H. Homayoun;Avesta Sasan
随着卷积神经网络（CNN）在计算机视觉领域越来越成为一种商品，许多人试图改进CNN，以实现更好的准确性，以至于CNN的准确性已经超过了人类的能力。然而，随着网络的深入，计算的数量以及每个分类所需的功率已经大大增加。在本文中，我们提出了迭代CNN（ICNN），将CNN从单个前馈网络重新定义为一系列顺序执行的较小网络。每个较小的网络处理输入图像的一个子样本，以及从前一个网络中提取的特征，并提高分类精度。一旦达到可接受的分类置信度，ICNN立即终止。所提出的网络架构允许通过创建提前终止的可能性来动态地近似CNN函数，并且与传统CNN相比，使用少得多的操作来执行分类。我们的研究结果表明，这种迭代方法在准确性方面与原始的大型网络竞争，同时通过在早期迭代中检测许多图像而产生的计算复杂度要低得多。
With Convolutional Neural Networks (CNN) becoming more of a commodity in the computer vision field, many have attempted to improve CNN in a bid to achieve better accuracy to a point that CNN accuracies have surpassed that of human's capabilities. However, with deeper networks, the number of computations and consequently the power needed per classification has grown considerably. In this paper, we propose Iterative CNN (ICNN) by reformulating the CNN from a single feed-forward network to a series of sequentially executed smaller networks. Each smaller network processes a sub-sample of input image, and features extracted from previous network, and enhances the classification accuracy. Upon reaching an acceptable classification confidence, ICNN immediately terminates. The proposed network architecture allows the CNN function to be dynamically approximated by creating the possibility of early termination and performing the classification with far fewer operations compared to a conventional CNN. Our results show that this iterative approach competes with the original larger networks in terms of accuracy while incurring far less computational complexity by detecting many images in early iterations.