ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 RRNet: Repetition-Reduction Network for Energy Efficient Depth Estimation
Cited 3 time in scopus Download 118 time Share share facebook twitter linkedin kakaostory
저자
오상윤, 김혜진, 이종은, 김준모
발행일
202006
출처
IEEE Access, v.8, pp.106097-106108
ISSN
2169-3536
출판사
IEEE
DOI
https://dx.doi.org/10.1109/ACCESS.2020.3000773
협약과제
20PS1400, 세라믹산업 제조혁신을 위한 클라우드 기반 빅데이터 플랫폼 개발, 지수영
초록
Lightweight neural networks that employ depthwise convolution have a significant computational advantage over those that use standard convolution because they involve fewer parameters; however, they also require more time, even with graphics processing units (GPUs). We propose a Repetition-Reduction Network (RRNet) in which the number of depthwise channels is large enough to reduce computation time while simultaneously being small enough to reduce GPU latency. RRNet also reduces power consumption and memory usage, not only in the encoder but also in the residual connections to the decoder. We apply RRNet to the problem of resource-constrained depth estimation, where it proves to be significantly more efficient than other methods in terms of energy consumption, memory usage, and computation. It has two key modules: the Repetition-Reduction (RR) block, which is a set of repeated lightweight convolutions that can be used for feature extraction in the encoder, and the Condensed Decoding Connection (CDC), which can replace the skip connection, delivering features to the decoder while significantly reducing the channel depth of the decoder layers. Experimental results on the KITTI dataset show that RRNet consumes 3.84\times less energy and 3.06\times less memory than conventional schemes, and that it is 2.21\times faster on a commercial mobile GPU without increasing the demand on hardware resources relative to the baseline network. Furthermore, RRNet outperforms state-of-the-art lightweight models such as MobileNets, PyDNet, DiCENet, DABNet, and EfficientNet.
KSP 제안 키워드
Baseline network, Channel depth, Depth estimation, Feature extractioN, Graphic Processing Unit(GPU), Hardware Resources, Lightweight model, Mobile GPU, Power Consumption, Resource-constrained, computation time
본 저작물은 크리에이티브 커먼즈 저작자 표시 (CC BY) 조건에 따라 이용할 수 있습니다.
저작자 표시 (CC BY)