Binarized Encoder-Decoder Network and Binarized Deconvolution Engine for Semantic Segmentation
Hyunwoo Kim, Jeonghoon Kim, Jungwook Choi, Jungkeol Lee, Yong Ho Song · IEEE Access · 2020
Recently, semantic segmentation based on deep neural network (DNN) has attracted attention as it exhibits high accuracy, and many studies have been conducted on this. However, DNN-based segmentation studies focused mainly on improving accuracy, thus greatly increasing the computational demand and memory footprint of the segmentation network. For this reason, the segmentation network requires a lot of hardware resources and power consumption, and it is difficult to be applied to an environment where they are limited, such as an embedded system. In this paper, we propose a binarized encoder-decoder network (BEDN) and a binarized deconvolution engine (BiDE) accelerating the network to realize low-power, real-time semantic segmentation.BiDEimplements a binarized segmentation network with custom hardware, greatly reducing the hardware resource usage and greatly increasing the throughput of network implementation. The deconvolution used for upsampling in a segmentation network includes zero padding. In order to enable deconvolution in a binarized segmentation network that cannot express zero, we introducezero-aware binarized deconvolutionwhich skips padded zero activations andzero-aware batch normalization embedded binary activationconsidering zero-skipped convolution. TheBEDN, which is a binarized segmentation network proposed to be accelerated onBiDE, has acceptable accuracy while greatly reducing the computational and memory demands of the segmentation network through full-binarization and simple structure.BEDNhas a network size of 0.21 MB, and its maximum memory usage is 1.38 MB.BiDEwas implemented on Xilinx ZU7EV field-programmable gate array (FPGA) to operate at 187.5 MHz.BiDEaccelerated the proposedBEDNwithin CamVid11 images of$480\times {360}$size at 25.89 frames per second (FPS) achieving a performance of 1.682 Tera operations per second (TOPS) and 824 Giga operations per second per watt (GOPS/W).