paper-with-me

홈 › Papers

Pelee: A Real-Time Object Detection System on Mobile Devices

2018-04-18 · NeurIPS 2018 · Robert J. Wang, Xiang Li, Charles X. Ling

An increasing need of running Convolutional Neural Network (CNN) models on mobile devices with limited computing power and memory resource encourages studies on efficient model design. A number of efficient architectures have been proposed in recent years, for example, MobileNet, ShuffleNet, and MobileNetV2. However, all these models are heavily dependent on depthwise separable convolution which lacks efficient implementation in most deep learning frameworks. In this study, we propose an efficient architecture named PeleeNet, which is built with conventional convolution instead. On ImageNet ILSVRC 2012 dataset, our proposed PeleeNet achieves a higher accuracy and over 1.8 times faster speed than MobileNet and MobileNetV2 on NVIDIA TX2. Meanwhile, PeleeNet is only 66% of the model size of MobileNet. We then propose a real-time object detection system by combining PeleeNet with Single Shot MultiBox Detector (SSD) method and optimizing the architecture for fast speed. Our proposed detection system2, named Pelee, achieves 76.4% mAP (mean average precision) on PASCAL VOC2007 and 22.4 mAP on MS COCO dataset at the speed of 23.6 FPS on iPhone 8 and 125 FPS on NVIDIA TX2. The result on COCO outperforms YOLOv2 in consideration of a higher precision, 13.6 times lower computational cost and 11.3 times smaller model size.

📄 PDF Abstract BibTeX arXiv:1804.06882

Code (9)

Baibaifan/An-Improved-PeleeNet-Algorithm-with-Feature-Pyramid-Networks-for-Image-Detection- tf
PaddlePaddle/PaddleClas paddle
Qengineering/PeleeNet_SSD
flytocc/PeleeNet-paddle paddle
ginn24/Pelee-TensorRT
koshian2/PeleeNet-Keras tf
osmr/imgclsmob mxnet
wpf535236337/pytorch-peleenet pytorch
yxlijun/Pelee.Pytorch pytorch

Tasks

object-detectionObject DetectionReal-Time Object Detection

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Pelee: A Real-Time Object Detection System on Mobile Devices

2018-12-01 · NeurIPS 2018 12 · Jun Wang, Tanner Bohn, Charles Ling

An increasing need of running Convolutional Neural Network (CNN) models on mobile devices with limited computing power and memory resource encourages studies on efficient model design. A number of efficient architectures…

object-detectionObject DetectionReal-Time Object Detection

The Power of Tiling for Small Object Detection

2019-06-11 · Computer Vision and Pattern Recognition 2019 6 · F. Ozge UnelBurak OzkalayciCevahir Cigla

Deep neural network based techniques are state-of-the-art for object detection and classification with the help ofthe development in computational power and memory ef-ficiency. Although these networks are adapted for mob…

Objectobject-detectionObject DetectionSmall Object Detection

Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages

2018-07-29 · Yuxi Li, Jiuwei Li, Weiyao Lin, Jianguo Li

Object detection has made great progress in the past few years along with the development of deep learning. However, most current object detection methods are resource hungry, which hinders their wide deployment to many …

Objectobject-detectionObject Detection

Selective Convolutional Network: An Efficient Object Detector with Ignoring Background

2020-02-04 · Hefei Ling, Yangyang Qin, Li Zhang, Yuxuan Shi 외

It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors. Instead of refining feature maps prevalently, we reduce the prohibitive computational complexity…

TOG: Targeted Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems

2020-04-09 · Ka-Ho Chow, Ling Liu, Mehmet Emre Gursoy, Stacey Truex 외

The rapid growth of real-time huge data capturing has pushed the deep learning and data analytic computing to the edge systems. Real-time object recognition on the edge is one of the representative deep neural network (D…

Autonomous DrivingObjectobject-detectionObject Detection+3