ICNN: The Iterative Convolutional Neural Network
ICNN: The Iterative Convolutional Neural Network
复制标题
DOI：
10.1145/3355553
复制
发表时间：
2020-01-01
影响因子：
2
通讯作者：
Sasan, Avesta
中科院分区：
文献类型：
--
作者：
Neshatpour, Katayoun;Homayoun, Houman;Sasan, Avesta
基于视觉的卷积神经网络（CNN）的现代和最新架构显着提高了检测和预测精度。然而，这些算法是非常计算密集型的。为了打破CNN计算的功率和性能墙，我们将CNN计算重新公式化为迭代过程，其中每次迭代使用较小的网络处理输入特征的子样本，并摄取额外的特征以提高预测精度。每个较小的网络可以根据其输入集进行分类，或者将计算和提取的特征馈送到下一个网络以提高准确性。所提出的方法允许在达到可接受的置信度时提前终止。此外，每个迭代提供上下文感知，其允许针对进行中的迭代的智能资源分配和优化。在这篇文章中，我们提出了各种策略，通过所提出的迭代方法来降低CNN的计算复杂度。我们说明了所提出的政策如何构建一个动态的体系结构，适用于各种应用程序的精度要求，资源和时间预算，而不需要进一步的网络重新训练。此外，我们通过反卷积网络对每次迭代中检测到的特征进行可视化，以更深入地了解ICNN的连续遍历。
Modern and recent architectures of vision-based Convolutional Neural Networks (CNN) have improved detection and prediction accuracy significantly. However, these algorithms are extremely computationally intensive. To break the power and performance wall of CNN computation, we reformulate the CNN computation into an iterative process, where each iteration processes a sub-sample of input features with smaller network and ingests additional features to improve the prediction accuracy. Each smaller network could either classify based on its input set or feed computed and extracted features to the next network to enhance the accuracy. The proposed approach allows early-termination upon reaching acceptable confidence. Moreover, each iteration provides a contextual awareness that allows an intelligent resource allocation and optimization for the proceeding iterations. In this article, we propose various policies to reduce the computational complexity of CNN through the proposed iterative approach. We illustrate how the proposed policies construct a dynamic architecture suitable for a wide range of applications with varied accuracy requirements, resources, and time-budget, without further need for network re-training. Furthermore, we carry out a visualization of the detected features in each iteration through deconvolution network to gain more insight into the successive traversal of the ICNN.