ThunderNet: Towards Real-time Generic Object Detection

Abstract

Real-time generic object detection on mobile platforms is a crucial but challenging computer vision task. However, previous CNN-based detectors suffer from enormous computational cost, which hinders them from real-time inference in computation-constrained scenarios. In this paper, we investigate the effectiveness of two-stage detectors in real-time generic detection and propose a lightweight two-stage detector named ThunderNet. In the backbone part, we analyze the drawbacks in previous lightweight backbones and present a lightweight backbone designed for object detection. In the detection part, we exploit an extremely efficient RPN and detection head design. To generate more discriminative feature representation, we design two efficient architecture blocks, Context Enhancement Module and Spatial Attention Module. At last, we investigate the balance between the input resolution, the backbone, and the detection head. Compared with lightweight one-stage detectors, ThunderNet achieves superior performance with only 40% of the computational cost on PASCAL VOC and COCO benchmarks. Without bells and whistles, our model runs at 24.1 fps on an ARM-based device. To the best of our knowledge, this is the first real-time detector reported on ARM platforms. Our code and models are available at \url{https://github.com/qinzheng93/ThunderNet}.

arXiv commentAccepted by ICCV 2019. Code and models available at https://github.com/qinzheng93/ThunderNet

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• YOLOv3: An Incremental Improvement
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• DSSD : Deconvolutional Single Shot Detector
• Cascade R-CNN: Delving into High Quality Object Detection
• Light-Head R-CNN: In Defense of Two-Stage Object Detector
• Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages

Cited by in corpus (8)

• CSPNet: A New Backbone that can Enhance Learning Capability of CNN
• DetNAS: Backbone Search for Object Detection
• AugFPN: Improving Multi-scale Feature Learning for Object Detection
• EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
• SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
• MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices
• Adaptive Class Suppression Loss for Long-Tail Object Detection
• BiDet: An Efficient Binarized Object Detector