YOLO Nano: a Highly Compact You Only Look Once Convolutional Neural Network for Object Detection

TL;DR

YOLO Nano is a highly compact and efficient object detection neural network designed for edge devices, achieving high accuracy with significantly reduced size and computational requirements compared to Tiny YOLO variants.

Contribution

The paper introduces YOLO Nano, a novel compact neural network architecture for object detection, developed through a human-machine collaborative design process for embedded applications.

Findings

Model size of ~4.0MB, much smaller than Tiny YOLO variants.

Achieves ~69.1% mAP on VOC 2007, outperforming Tiny YOLOv2 and Tiny YOLOv3.

Requires fewer operations, suitable for embedded devices.

Abstract

Object detection remains an active area of research in the field of computer vision, and considerable advances and successes has been achieved in this area through the design of deep convolutional neural networks for tackling object detection. Despite these successes, one of the biggest challenges to widespread deployment of such object detection networks on edge and mobile scenarios is the high computational and memory requirements. As such, there has been growing research interest in the design of efficient deep neural network architectures catered for edge and mobile usage. In this study, we introduce YOLO Nano, a highly compact deep convolutional neural network for the task of object detection. A human-machine collaborative design strategy is leveraged to create YOLO Nano, where principled network design prototyping, based on design principles from the YOLO family of single-shot object detection network architectures, is coupled with machine-driven design exploration to create a compact network with highly customized module-level macroarchitecture and microarchitecture designs tailored for the task of embedded object detection. The proposed YOLO Nano possesses a model size of ~4.0MB (>15.1x and >8.3x smaller than Tiny YOLOv2 and Tiny YOLOv3, respectively) and requires 4.57B operations for inference (>34% and ~17% lower than Tiny YOLOv2 and Tiny YOLOv3, respectively) while still achieving an mAP of ~69.1% on the VOC 2007 dataset (~12% and ~10.7% higher than Tiny YOLOv2 and Tiny YOLOv3, respectively). Experiments on inference speed and power efficiency on a Jetson AGX Xavier embedded module at different power budgets further demonstrate the efficacy of YOLO Nano for embedded scenarios.