Rapid Exact Signal Scanning with Deep Convolutional Neural Networks

Abstract

A rigorous formulation of the dynamics of a signal processing scheme aimed at dense signal scanning without any loss in accuracy is introduced and analyzed. Related methods proposed in the recent past lack a satisfactory analysis of whether they actually fulfill any exactness constraints. This is improved through an exact characterization of the requirements for a sound sliding window approach. The tools developed in this paper are especially beneficial if Convolutional Neural Networks are employed, but can also be used as a more general framework to validate related approaches to signal scanning. The proposed theory helps to eliminate redundant computations and renders special case treatment unnecessary, resulting in a dramatic boost in efficiency particularly on massively parallel processors. This is demonstrated both theoretically in a computational complexity analysis and empirically on modern parallel processors.

Pages 1-16 only: Copyright (c) 2016 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fully Convolutional Networks for Semantic Segmentation
• cuDNN: Efficient Primitives for Deep Learning
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
• Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification
• Rapid Exact Signal Scanning with Deep Convolutional Neural Networks
• ZNNi - Maximizing the Inference Throughput of 3D Convolutional Networks on Multi-Core CPUs and GPUs

Cited by in corpus (2)

• Rapid Exact Signal Scanning with Deep Convolutional Neural Networks
• Robust Deep-Learning-Based Road-Prediction for Augmented Reality Navigation Systems