SkyNet, a lightweight 12-layer DNN with 1.82 MB parameters, won first place in the DAC-SDC low-power UAV object detection contest, achieving 0.731 IoU at 67.33 FPS on TX2 GPU and 0.716 IoU at 25.05 FPS on Ultra96 FPGA.
H.; Rupnow, K.; Xiong, J.; Hwu, W.-M.; and Chen, D
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection
SkyNet, a lightweight 12-layer DNN with 1.82 MB parameters, won first place in the DAC-SDC low-power UAV object detection contest, achieving 0.731 IoU at 67.33 FPS on TX2 GPU and 0.716 IoU at 25.05 FPS on Ultra96 FPGA.