Comparison between Frame-Constrained Fix-Pixel-Value and Frame-Free Spiking-Dynamic-Pixel ConvNets for Visual Processing.
Comparison between Frame-Constrained Fix-Pixel-Value and Frame-Free Spiking-Dynamic-Pixel ConvNets for Visual Processing.
复制标题
DOI：
10.3389/fnins.2012.00032
复制
发表时间：
2012
影响因子：
4.3
通讯作者：
Linares-Barranco B
中科院分区：
文献类型：
--
作者：
Farabet C;Paz R;Pérez-Carrasco J;Zamarreño-Ramos C;Linares-Barranco A;Lecun Y;Culurciello E;Serrano-Gotarredona T;Linares-Barranco B
大多数用于提取图像和块中的特征的场景分割和分类体系结构都充分利用2D卷积运算来进行模板匹配、模板搜索和去噪。卷积神经网络(ConvNets)是可以实现通用生物启发视觉系统的这种体系结构的一个例子。在标准的数字计算机中，2D卷积通常在资源消耗方面是昂贵的，并且对高效的实时应用造成严重的限制。然而，受神经皮质启发的解决方案，如专用的基于帧的或无帧的尖峰ConvNet卷积处理器，正在推动实时视觉处理。这两种方法共享神经灵感，但它们各自以不同的方式解决问题。基于帧的ConvNets以非常健壮和快速的方式逐帧处理视频信息，这需要使用和共享可用的硬件资源(如：乘法器、加法器)。硬件资源通过取入和取出数据来进行固定和时分复用。因此，内存带宽和大小对于良好的性能非常重要。另一方面，基于尖峰的卷积处理器是一种无帧的替代方案，能够以非常低的延迟执行基于尖峰的视觉信息源的卷积，这使得非常适合于非常高速的应用。然而，硬件资源需要始终可用，并且不能进行时分复用。因此，硬件应该是模块化的、可重新配置的和可扩展的。VLSI定制集成电路(数字和模拟)和现场可编程门阵列的硬件实现已经用于演示这些系统的性能。在这篇文章中，我们提出了这两个神经启发解决方案的比较研究。对这两种制度进行了简要的描述，并讨论了它们的区别和优缺点。
Most scene segmentation and categorization architectures for the extraction of features in images and patches make exhaustive use of 2D convolution operations for template matching, template search, and denoising. Convolutional Neural Networks (ConvNets) are one example of such architectures that can implement general-purpose bio-inspired vision systems. In standard digital computers 2D convolutions are usually expensive in terms of resource consumption and impose severe limitations for efficient real-time applications. Nevertheless, neuro-cortex inspired solutions, like dedicated Frame-Based or Frame-Free Spiking ConvNet Convolution Processors, are advancing real-time visual processing. These two approaches share the neural inspiration, but each of them solves the problem in different ways. Frame-Based ConvNets process frame by frame video information in a very robust and fast way that requires to use and share the available hardware resources (such as: multipliers, adders). Hardware resources are fixed- and time-multiplexed by fetching data in and out. Thus memory bandwidth and size is important for good performance. On the other hand, spike-based convolution processors are a frame-free alternative that is able to perform convolution of a spike-based source of visual information with very low latency, which makes ideal for very high-speed applications. However, hardware resources need to be available all the time and cannot be time-multiplexed. Thus, hardware should be modular, reconfigurable, and expansible. Hardware implementations in both VLSI custom integrated circuits (digital and analog) and FPGA have been already used to demonstrate the performance of these systems. In this paper we present a comparison study of these two neuro-inspired solutions. A brief description of both systems is presented and also discussions about their differences, pros and cons.
登录
查看更多内容
影响因子：
2.5
作者：
Azevedo, Frederico A. C.;Carvalho, Ludmila R. B.;Herculano-Houzel, Suzana
通讯作者：
Herculano-Houzel, Suzana
影响因子：
5.4
作者：
Antonio Lenero-Bardallo, Juan;Serrano-Gotarredona, Teresa;Linares-Barranco, Bernabe
通讯作者：
Linares-Barranco, Bernabe
DOI：
10.1109/tcsi.2007.893509
发表时间：
2007-05-01
影响因子：
5.1
作者：
Chicca, Elisabetta;Whatley, Adrian M.;Indiveri, Giacomo
通讯作者：
Indiveri, Giacomo
DOI：
10.1109/tcsi.2006.887979
发表时间：
2007-01-01
影响因子：
5.1
作者：
Chan, Vincent;Liu, Shih-Chii;van Schaik, Andre
通讯作者：
van Schaik, Andre
DOI：
10.1109/tcsi.2007.900179
发表时间：
2007-07-01
影响因子：
5.1
作者：
Costas-Santos, Jesus;Serrano-Gotarredona, Teresa;Linares-Barranco, Bernabe
通讯作者：
Linares-Barranco, Bernabe