LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems

Subarna Tripathi, Gokce Dane, Byeongkeun Kang, Vasudev Bhaskaran, Truong Nguyen; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 94-103

Abstract


Deep convolutional Neural Networks (CNN) are the state-of-the-art performers for object detection task. It is well known that object detection requires more computation and memory than image classification. Thus the consolidation of a CNN-based object detection for an embedded system is more challenging. In this work, we propose LCDet, a fully-convolutional neural network for generic object detection that aims to work in embedded systems. We design and develop an end-to-end TensorFlow(TF)-based model. Additionally, we employ 8-bit quantization on the learned weights. We use face detection as a use case. Our TF-Slim based network can predict different faces of different shapes and sizes in a single forward pass. Our experimental results show that the LCDet achieves comparative accuracy comparing with state-of-the-art CNN-based face detection methods, while reducing the model size by 12x and memory-BW by 16x comparing with one of the best real-time CNN-based object detectors YOLO.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Tripathi_2017_CVPR_Workshops,
author = {Tripathi, Subarna and Dane, Gokce and Kang, Byeongkeun and Bhaskaran, Vasudev and Nguyen, Truong},
title = {LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {July},
year = {2017}
}