RRNet: Repetition-Reduction Network for Energy Efficient Depth Estimation

Cited 0 time in webofscience Cited 2 time in scopus
  • Hit : 272
  • Download : 174
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 less energy and less memory than conventional schemes, and that it is 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.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2020-05
Language
English
Article Type
Article
Citation

IEEE ACCESS, v.8, pp.106097 - 106108

ISSN
2169-3536
DOI
10.1109/ACCESS.2020.3000773
URI
http://hdl.handle.net/10203/275507
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
RRNet-RepetitionReduction-Network-for-Energy-Ef...(2.06 MB)Download

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0