ResNet-like Architecture with Low Hardware Requirements

One of the most computationally intensive parts in modern recognition systems is an inference of deep neural networks that are used for image classification, segmentation, enhancement, and recognition. The growing popularity of edge computing makes us look for ways to reduce its time for mobile and embedded devices.One way to decrease the neural network inference time is to modify a neuron model to make it moreefficient for computations on a specific device. The example ofsuch a model is a bipolar morphological neuron model. The bipolar morphological neuron is based on the idea of replacing multiplication with addition and maximum operations. This model has been demonstrated for simple image classification with LeNet-like architectures [1]. In the paper, we introduce a bipolar morphological ResNet (BM-ResNet) model obtained from a much more complex ResNet architecture by converting its layers to bipolar morphological ones. We apply BM-ResNet to image classification on MNIST and CIFAR-10 datasets with only a moderate accuracy decrease from 99.3% to 99.1% and from 85.3% to 85.1%. We also estimate the computational complexity of the resulting model. We show that for the majority of ResNet layers, the considered model requires 2.1-2.9 times fewer logic gates for implementation and 15-30% lower latency.

硬件要求低的类似ResNet的体系结构

现代识别系统中计算量最大的部分之一是对用于图像分类，分割，增强和识别的深度神经网络的推论。边缘计算的日益普及使我们寻求减少移动和嵌入式设备使用时间的方法。.. 减少神经网络推理时间的一种方法是修改神经元模型，使其在特定设备上的计算效率更高。这种模型的例子是双极形态神经元模型。双极形态神经元是基于用加法和最大运算代替乘法的思想。已经证明了该模型可用于类似LeNet的体系结构进行简单的图像分类[1]。在本文中，我们介绍了一种双极性形态ResNet（BM-ResNet）模型，该模型是通过将更复杂的ResNet体系结构的层转换为双极性形态而获得的。我们将BM-ResNet应用于MNIST和CIFAR-10数据集的图像分类中，准确度仅从99.3％降至99.1％，从85.3％降至85.1％。我们还估计了所得模型的计算复杂性。 （阅读更多）