基于异构硬件系统的高效卷积神经网络像素分类
Efficient Convolutional Neural Networks for Pixelwise Classification on Heterogeneous Hardware Systems
摘要：
这项工作提出并分析了三个卷积神经网络（CNN）模型，用于有效的图像逐像素分类。当使用卷积神经网络对整幅图像的小块中的单个像素进行分类时，当使用滑动窗口网络时执行大量冗余计算。这组新架构通过删除冗余计算或使用完全卷积的架构来解决这个问题，这些架构本身就可以一次预测许多像素。这三个模型的实现可以通过Caffe库上的一个新实用程序访问。该实用程序支持各种图像输入和输出格式、预处理参数以及在训练期间均衡标签直方图的方法。Caffe库已经通过新的层和新的后端进行了扩展，以便通过OpenCL在更广泛的硬件（如CPU和GPU）上可用。在AMD GPU上，以SK等效SW（滑动窗口）网络为基准，观察到$54\times$（SK-Net）、$437\times$（U-Net）和$320\times$（USK-Net）的加速。标签吞吐量高达每秒一百万像素。所分析的神经网络具有在训练或处理期间应用的独特特征，并且不是每个数据集都适合于每个架构。在两个神经组织数据集上评估预测的质量，其中一个是ISBI 2012挑战数据集。在训练期间使用两种不同的损失函数，Malis损失和Softmax损失。整个管道，包括模型，界面和修改的Caffe库，可作为开源软件在工作名称Project Greentea下使用。
英文摘要：
This work presents and analyzes three convolutional neural network (CNN) models for efficient pixelwise classification of images. When using convolutional neural networks to classify single pixels in patches of a whole image, a lot of redundant computations are carried out when using sliding window networks. This set of new architectures solve this issue by either removing redundant computations or using fully convolutional architectures that inherently predict many pixels at once. The implementations of the three models are accessible through a new utility on top of the Caffe library. The utility provides support for a wide range of image input and output formats, pre-processing parameters and methods to equalize the label histogram during training. The Caffe library has been extended by new layers and a new backend for availability on a wider range of hardware such as CPUs and GPUs through OpenCL. On AMD GPUs, speedups of $54\times$ (SK-Net), $437\times$ (U-Net) and $320\times$ (USK-Net) have been observed, taking the SK equivalent SW (sliding window) network as the baseline. The label throughput is up to one megapixel per second. The analyzed neural networks have distinctive characteristics that apply during training or processing, and not every data set is suitable to every architecture. The quality of the predictions is assessed on two neural tissue data sets, of which one is the ISBI 2012 challenge data set. Two different loss functions, Malis loss and Softmax loss, were used during training. The whole pipeline, consisting of models, interface and modified Caffe library, is available as Open Source software under the working title Project Greentea.
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。
