2018

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

Li, Yuxi, Li, Jiuwei, Lin, Weiyao et al.

Understand

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 resource restricted usages such as usages on always-on devices, battery-powered low-end devices, etc.
This paper considers the resource and accuracy trade-off for resource-restricted usages during designing the whole object detection framework.
Based on the deeply supervised object detection (DSOD) framework, we propose Tiny-DSOD dedicating to resource-restricted usages.

Built on

The pascal visual object classes (voc) challenge
Mark Everingham, Luc Van Gool, Christopher Williams, John Winn, and Andrew Zisserman · 2010
Earlier work this paper cites.
Understanding the difficulty of training deep feedforward neural networks
Xavier Glorot and Yoshua Bengio · 2010
Earlier work this paper cites.
Are we ready for autonomous driving? the kitti vision benchmark suite
Andreas Geiger, Philip Lenz, and Raquel Urtasun · 2012
Earlier work this paper cites.
Selective search for object recognition
Jasper RR Uijlings, Koen EA Van De Sande, Theo Gevers, and Arnold WM Smeulders · 2013
Earlier work this paper cites.
Rich feature hierarchies for accurate object detection and semantic segmentation
Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik · 2014
Earlier work this paper cites.
Caffe: Convolutional architecture for fast feature embedding
Original
Yangqing Jia, Evan Shelhamer, Jeff Donahue, et al · 2014
Earlier work this paper cites.
Microsoft coco: Common objects in context
Tsung Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, et al · 2014
Earlier work this paper cites.
Very deep convolutional networks for large-scale image recognition
Karen Simonyan and Andrew Zisserman · 2014
Earlier work this paper cites.
Fast r-cnn
Ross Girshick · 2015
Earlier work this paper cites.
Parsenet: Looking wider to see better
Original
Wei Liu, Andrew Rabinovich, and Alexander C Berg · 2015
Earlier work this paper cites.
Faster r-cnn: towards real-time object detection with region proposal networks
Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun · 2015
Earlier work this paper cites.

Similar

Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, et al · 2015
Cited alongside, same era.
Shallow networks for high-accuracy road object-detection
Original
Khalid Ashraf, Bichen Wu, et al · 2016
Cited alongside, same era.
A unified multi-scale deep convolutional neural network for fast object detection
Zhaowei Cai, Quanfu Fan, Rogerio S. Feris, and Nuno Vasconcelos · 2016
Cited alongside, same era.
Xception: Deep learning with depthwise separable convolutions
Francois Chollet · 2016
Cited alongside, same era.
R-fcn: Object detection via region-based fully convolutional networks
Jifeng Dai, Yi Li, Kaiming He, and Jian Sun · 2016
Cited alongside, same era.
Deep residual learning for image recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun · 2016
Cited alongside, same era.
Squeezenet: Alexnet-level accuracy with 50x fewer parameters and ¡0.5 mb model size
Forrest N Iandola, Song Han, et al · 2016
Cited alongside, same era.
Ssd: Single shot multibox detector
Wei Liu, Dragomir Anguelov, Dumitru Erhan, et al · 2016
Cited alongside, same era.
Yolo9000: Better, faster, stronger
Joseph Redmon and Ali Farhadi · 2016
Cited alongside, same era.
You only look once: Unified, real-time object detection
Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi · 2016
Cited alongside, same era.
Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection
Original
Xiang, Yu and Choi, Wongun and Lin, Yuanqing and Savarese, Silvio · 2016
Cited alongside, same era.
Densely connected convolutional networks
Gao Huang, Zhuang Liu, Laurens Van De Maaten, and Kilian Q. Weinberger
Cited in the paper.

Then

Dssd : Deconvolutional single shot detector
Original
Cheng Yang Fu, Wei Liu, Ananth Ranga, Ambrish Tyagi, and Alex Berg · 2017
Later among the works it cites.
Mask r-cnn
Kaiming He, Georgia Gkioxari, Piotr Dollár, et al · 2017
Later among the works it cites.
Mobilenets: Efficient convolutional neural networks for mobile vision applications
Original
Andrew Howard, Menglong Zhu, et al · 2017
Later among the works it cites.
Feature pyramid networks for object detection
Tsung Yi Lin, Piotr Dollar, Ross Girshick, Kaiming He, et al · 2017
Later among the works it cites.
Dsod: Learning deeply supervised object detectors from scratch
Zhiqiang Shen, Zhuang Liu, Jianguo Li, et al · 2017
Later among the works it cites.
Squeezedet: Unified, small, low power fully convolutional neural networks for real-time object detection for autonomous driving
Bichen Wu, Forrest Iandola, et al · 2017
Later among the works it cites.
Condensenet: An efficient densenet using learned group convolutions
Gao Huang, Shichen Liu, Van Der Maaten Laurens, and Kilian Q Weinberger · 2018
Closest in time.
Pelee: A real-time object detection system on mobile devices
Xiang Li Robert Wang, Shuang Ao and Charles X. Ling · 2018
Closest in time.
Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation
Original
Mark Sandler, Andrew Howard, Menglong Zhu, et al · 2018
Closest in time.
Context-aware single-shot detector
Wei Xiang, Dong Qing Zhang, Vassilis Athitsos, and Heather Yu · 2018
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…