DT-CNN: An Energy-Efficient Dilated and Transposed Convolutional Neural Network Processor for Region of Interest Based Image Segmentation

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 31
  • Download : 0
An energy-efficient convolutional neural network (CNN) processor is proposed for real-time image segmentation on mobile devices. The proposed processor utilizes Region of Interest (ROI) based image segmentation to speed up the process and reduce the overall external memory access. Although the ROI based image segmentation degrades the segmentation accuracy, the proposed dilation rate adjustment algorithm, which regulates the receptive field depending on the ROI resolution during dilated convolution, compensates for the accuracy degradation up to 0.2310 mean Intersection over Union (mIoU). In addition, the processor accelerates the dilated and transposed convolution by skipping the redundant zero computations with the proposed delay cells. As a result, the throughput of dilated and transposed convolution is increased up to x159 and x3.84. The delay cells can also support the variable dilation rates in dilated convolution caused by the dilation rate adjustment algorithm. Moreover, the processor selects the operating frequency based on the ROI resolution to save power consumption up to 81.2%. The processor is simulated in 65 nm CMOS technology, and the 6.8 mm(2) processor consumes the 206 mW power consumption with the 4.66 ms of processing time and 3.22 TOPS/W energy-efficiency at the target image segmentation dataset.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2020-10
Language
English
Article Type
Article; Proceedings Paper
Citation

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, v.67, no.10, pp.3471 - 3483

ISSN
1549-8328
DOI
10.1109/TCSI.2020.2991189
URI
http://hdl.handle.net/10203/276919
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0