RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices

Abstract

Previous state-of-the-art real-time object detectors have been reported on GPUs which are extremely expensive for processing massive data and in resource-restricted scenarios. Therefore, high efficiency object detectors on CPU-only devices are urgently-needed in industry. The floating-point operations (FLOPs) of networks are not strictly proportional to the running speed on CPU devices, which inspires the design of an exactly "fast" and "accurate" object detector. After investigating the concern gaps between classification networks and detection backbones, and following the design principles of efficient networks, we propose a lightweight residual-like backbone with large receptive fields and wide dimensions for low-level features, which are crucial for detection tasks. Correspondingly, we also design a light-head detection part to match the backbone capability. Furthermore, by analyzing the drawbacks of current one-stage detector training strategies, we also propose three orthogonal training strategies---IOU-guided loss, classes-aware weighting method and balanced multi-task training approach. Without bells and whistles, our proposed RefineDetLite achieves 26.8 mAP on the MSCOCO benchmark at a speed of 130 ms/pic on a single-thread CPU. The detection accuracy can be further increased to 29.6 mAP by integrating all the proposed training strategies, without apparent speed drop.

arXiv comment16 pages, 8 figures

References in corpus (17)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• YOLOv3: An Incremental Improvement
• Res2Net: A New Multi-scale Backbone Architecture
• DSSD : Deconvolutional Single Shot Detector
• UnitBox: An Advanced Object Detection Network
• Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression
• ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
• FSSD: Feature Fusion Single Shot Multibox Detector
• Beyond Skip Connections: Top-Down Modulation for Object Detection
• Light-Head R-CNN: In Defense of Two-Stage Object Detector
• DetNet: A Backbone network for Object Detection
• Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
• Improving Image Captioning with Conditional Generative Adversarial Nets
• Tiny SSD: A Tiny Single-shot Detection Deep Convolutional Neural Network for Real-time Embedded Object Detection
• Consistent Optimization for Single-Shot Object Detection