SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection

TL;DR

SkyNet is a highly efficient, lightweight deep neural network designed for real-time object detection on edge devices, achieving top performance in low power UAV image analysis competitions.

Contribution

Introduces SkyNet, a novel extremely lightweight DNN with 12 Conv layers and 1.82MB parameters, optimized for edge AI applications and demonstrated in a competitive UAV object detection challenge.

Findings

Achieved 0.731 IoU and 67.33 FPS on GPU

Achieved 0.716 IoU and 25.05 FPS on FPGA

Won first place in DAC-SDC low power object detection challenge

Abstract

Developing artificial intelligence (AI) at the edge is always challenging, since edge devices have limited computation capability and memory resources but need to meet demanding requirements, such as real-time processing, high throughput performance, and high inference accuracy. To overcome these challenges, we propose SkyNet, an extremely lightweight DNN with 12 convolutional (Conv) layers and only 1.82 megabyte (MB) of parameters following a bottom-up DNN design approach. SkyNet is demonstrated in the 56th IEEE/ACM Design Automation Conference System Design Contest (DAC-SDC), a low power object detection challenge in images captured by unmanned aerial vehicles (UAVs). SkyNet won the first place award for both the GPU and FPGA tracks of the contest: we deliver 0.731 Intersection over Union (IoU) and 67.33 frames per second (FPS) on a TX2 GPU and deliver 0.716 IoU and 25.05 FPS on an Ultra96 FPGA.