VoCaM: Visualization oriented convolutional neural network acceleration on mobile system: Invited paper
VoCaM: Visualization oriented convolutional neural network acceleration on mobile system: Invited paper
复制标题
DOI：
10.1109/iccad.2017.8203864
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
Zhuwei Qin;Zirui Xu;Qide Dong;Yiran Chen;Xiang Chen
中科院分区：
文献类型：
--
作者：
Zhuwei Qin;Zirui Xu;Qide Dong;Yiran Chen;Xiang Chen
卷积神经网络（CNN）作为各种计算机视觉任务最有前途的解决方案已被广泛研究。然而，CNN由于其复杂的网络计算流程而引入了大量的计算开销，导致适用性和性能显着降低，尤其是在移动设备上。主要基于模型压缩和堆叠外部计算资源提出了各种优化方案。虽然这些方案已被证明是有效的，但考虑到特定于移动设备的上下文感知优化方法的方法在很大程度上被忽视了。其中一个机会是对具有显着特征的被测对象进行可行的 CNN 计算流程简化，这些对象可以在移动传感器系统内部进行有效的预分析。因此，我们提出了 VoCaM，一种在移动设备上用于图像分类任务的面向可视化的 CNN 加速框架。 VoCaM 利用移动摄像头系统，可以进行全面的预分析，以揭示待测图像的颜色成分，而不会产生任何额外的开销。此外，VoCaM 的可视化分析表明，当被测图像具有不匹配的原色分量时，某些特定于颜色的滤镜可能会对结果产生非常微不足道的影响。然后对这些无关紧要的滤波器应用一套近似计算方法来代替密集的卷积运算，大大加速计算过程。在可忽略的开销下，VoCaM 可以显着优化卷积层的计算负载，对整体分类精度的影响非常小。
Convolutional Neural Networks (CNNs) have been widely investigated as some of the most promising solution for various computer vision tasks. However, CNNs introduce massive computing overhead due to their complex network computing flow, resulting in significantly reduced applicability and performance, especially in the mobile devices. Various optimization schemes have been proposed mainly based on both model compression and stacked external computing resources. While these schemes have been proven effective, methods which take into account mobile-specific context-aware optimization approaches have been largely overlooked. One such opportunity is the feasible CNN computing flow simplification to the under-test objects with distinguish features, which can be efficiently pre-analyzed inside the mobile sensor system. Hence, we propose VoCaM, a visualization oriented CNN acceleration framework on mobile devices for image classification tasks. VoCaM takes advantage of the mobile camera system, where the comprehensive pre-analysis can be conducted to reveal the color composition of the under-test images without incurring any additional overhead. Also, the visualization analysis of VoCaM reveals that, certain color-specific filters may have very trivial result impact when the under-test images have mismatching primary color components. Then a set of approximate computing methods is applied to these insignificant filters to replace the intensive convolutional operation, and greatly accelerate the computing process. With ignorable overhead, VoCaM can significantly optimize the computation load of the convolutional layers, with very small impact on the overall classification accuracy.