Efficient ConvNet for Surface Object Recognition

Surface object recognition plays an important role in surface detection system. Comparing with feature-based classifier, deep neural networks have evolved to the state-of-the-art technique for object recognition in complex background. However, excessive memory requirements, expensive computational costs and overmuch energy consumption make it difficult to deploy neural networks on embedded platform such as the environment perception module of the Unmanned surface vessel (USV). In this paper, we propose a dynamic-selecting criterion approach to prune a trained Yolo-v2 model to deal with these drawbacks caused by redundant parameters in network and we can reduce inference costs for Yolo-v2 by up to 65% on it while regaining close to the original performance by retraining the network. Moreover, we introduce a surface object dataset for surface detection system.

[1]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Vincent Vanhoucke,et al.  Improving the speed of neural networks on CPUs , 2011 .

[3]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Andrew Zisserman,et al.  Speeding up Convolutional Neural Networks with Low Rank Expansions , 2014, BMVC.

[5]  Pritish Narayanan,et al.  Deep Learning with Limited Numerical Precision , 2015, ICML.

[6]  Tonje Nanette Arnesen,et al.  Literature review on vessel detection , 2004 .

[7]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[8]  Geoffrey E. Hinton,et al.  An Alternative Model for Mixtures of Experts , 1994, NIPS.

[9]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Yixin Chen,et al.  Compressing Neural Networks with the Hashing Trick , 2015, ICML.

[11]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[12]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

[13]  Joan Bruna,et al.  Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation , 2014, NIPS.

[14]  Dumitru Erhan,et al.  Deep Neural Networks for Object Detection , 2013, NIPS.

[15]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Babak Hassibi,et al.  Second Order Derivatives for Network Pruning: Optimal Brain Surgeon , 1992, NIPS.

[17]  Kaiming He,et al.  Mask R-CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[18]  Jitendra Malik,et al.  Region-Based Convolutional Networks for Accurate Object Detection and Segmentation , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[20]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.

[22]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[23]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).