This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Semantic Segmentation with Inverted Residuals and Atrous Convolution
Technical Paper
2018-01-1635
ISSN: 0148-7191, e-ISSN: 2688-3627
This content contains downloadable datasets
Annotation ability available
Sector:
Language:
English
Abstract
Semantic segmentation has become a fundamental topic in the field of the computer vision, whose goal is to assign each pixel in the image to the corresponding category label. This topic is of broad interest for potential applications in automatic driving. Recently, modern frameworks of semantic segmentation are mostly based on the deep convolutional neural networks. And the general trend focus on increasing the accuracy of the framework, but at the cost of bringing extra parameters and making the network more complicated, which makes the network hard to implement on the vehicle mobile and embedded devices with limited computational resources. In this paper, a novel architecture is developed based on Inverted Residual and Atrous Convolution, in the sense that not only computation cost can be drastically reduced, but also high accuracy can still be maintained. In addition, two simple global hyper-parameters for seeking a tradeoff between accuracy and computation are introduced to build a model with appropriate size, which can operate in a computational limited platform. The experiments are performed on challenging CityScapes dataset and CamVid dataset. And the results are presented to demonstrate the good performance of the proposed architecture, in comparison with existing state-of-the-art methods. Furthermore, extensive experiments on the tradeoff between the resource and accuracy are also carried out. The results indicate that the model with appropriate size can be obtained by the choice of the two global hyper-parameters, which can be easily matched to the design requirements for mobile vision applications.
Authors
Citation
Kong, H., Fan, L., and Zhang, X., "Semantic Segmentation with Inverted Residuals and Atrous Convolution," SAE Technical Paper 2018-01-1635, 2018, https://doi.org/10.4271/2018-01-1635.Data Sets - Support Documents
Title | Description | Download |
---|---|---|
Unnamed Dataset 1 | ||
Unnamed Dataset 2 | ||
Unnamed Dataset 3 | ||
Unnamed Dataset 4 | ||
Unnamed Dataset 5 |
Also In
References
- He , K. , Zhang , X. , Ren , S. , and Sun , J. Deep Residual Learning for Image Recognition Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition USA June 27-30 2016 10.1109/CVPR.2016.90
- Badrinarayanan , V. , Kendall , A. , and Cipolla , R. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Scene Segmentation IEEE Transactions on Pattern Analysis and Machine Intelligence 39 12 2481 2495 2017 10.1109/TPAMI.2016.2644615
- Jonathan , L. , Shelhamer , E. , and Darrell , T. Fully Convolutional Networks for Semantic Segmentation Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition USA June 7-12 2015 10.1109/CVPR.2015.7298965
- Zhao , H. , Shi , J. , Qi , X. , Wang , X. , and Jia , J. Pyramid Scene Parsing Network IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) USA July 21-26 2017 10.1109/CVPR.2017.660
- Chen , L.C. , Papandreou , G. , Kokkinos , I. , Murphy , K. , and Yuille , A.L. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs IEEE Transactions on Pattern Analysis and Machine Intelligence 99 1 14 2017 10.1109/TPAMI.2017.2699184
- Sandler , M. , Howard , A. , Zhu , M. , Zhmoginov , A. , and Chen , L. C. arXiv arXiv 2018
- Chollet , F. Xception: Deep Learning With Depthwise Separable Convolutions Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition USA July 21-26 2017 10.1109/CVPR.2017.195
- Cordts , M. , Omran , M. , Ramos , S. , Rehfeld , T. et al. The Cityscapes Dataset for Semantic Urban Scene Understanding Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition USA June 27-30 2016 10.1109/CVPR.2016.350
- Brostow , G. J. , Shotton , J. , Fauqueur , J. , and Cipolla , R. Segmentation and Recognition Using Structure from Motion Point Clouds European Conference on Computer Vision France October 12-18 2008 10.1007/978-3-540-88682-2_5
- Shotton , J. , Johnson , M. , and Cipolla , R. Semantic Texton Forests for Image Categorization and Segmentation Computer Vision and Pattern Recognition USA June 23-28 2008 10.1109/CVPR.2008.4587503
- Fulkerson , B. , Vedaldi , A. , and Soatto , S. Class Segmentation and Object Localization with Super Pixel Neighborhoods IEEE 12th International Conference on Computer Vision Japan Sept. 29-Oct. 2 2009 10.1109/ICCV.2009.5459175
- Peng , C. , Zhang , X. , Yu , G. , Luo , G. , and Sun , J. Large Kernel Matters--Improve Semantic Segmentation by Global Convolutional Network Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition USA July 21-26 2017 10.1109/CVPR.2017.189
- Zheng , S. , Jayasumana , S. , Romera-Paredes , B. , Vineet , V. et al. Conditional Random Fields as Recurrent Neural Networks Proceedings of the IEEE International Conference on Computer Vision Chile Dec. 7-13 2015 10.1109/ICCV.2015.179
- Han , S. , Pool , J. , Tran , J. , and Dally , W. Learning Both Weights and Connections for Efficient Neural Network Advances in Neural Information Processing Systems 28 2015
- Wen , W. , Wu , C. , Wang , Y. , Chen , Y. et al. Learning Structured Sparsity in Deep Neural Networks Advances in Neural Information Processing Systems 29 2016
- Wu , J. , Leng , C. , Wang , Y. , Hu , Q. et al. Quantized Convolutional Neural Networks for Mobile Devices Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition USA June 27-30 2016 10.1109/CVPR.2016.521
- Jaderberg , M. , Vedaldi , A. , and Zisserman , A. arXiv arXiv 2014
- Hinton , G. , Vinyals , O. , and Dean , J. arXiv arXiv 2015
- Mathieu , M. Henaff , M. , and LeCun , Y. arXiv arXiv 2013
- Paszke , A. , Chaurasia , A. , Kim , S. , and Culurciello , E. arXiv arXiv 2016
- Iandola , F. N. , Han , S. , Moskewicz , M. W. , Ashraf , K. et al. arXiv arXiv 2016
- Howard , A. G. , Zhu , M. , Chen , B. , Kalenichenko , D. et al. arXiv arXiv 2017
- Zhang , X. , Zhou , X. , Lin , M. , and Sun , J. arXiv arXiv 2017
- Simonyan , K. and Zisserman , A. arXiv arXiv 2014
- Huang , G. , Liu , Z. , Weinberger , K. Q. et al. Densely Connected Convolutional Networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition USA July 21-26 2017 10.1109/CVPR.2017.243
- Xie , S. , Girshick , R. , Dollár , P. , Tu , Z. et al. Aggregated Residual Transformations for Deep Neural Networks Computer Vision and Pattern Recognition (CVPR) USA July 21-26 2017 10.1109/CVPR.2017.634
- Chen , L. C. , Papandreou , G. , Schroff , F. , and Adam , H. arXiv arXiv 2017
- Ren , S. , He , K. , Girshick , R. , and Sun , J. Faster r-cnn: Towards Real-Time Object Detection with Region Proposal Networks IEEE Transactions on Pattern Analysis and Machine Intelligence 39 6 1137 1149 2017 10.1109/TPAMI.2016.2577031
- Zhao , H. , Qi , X. , Shen , X. , Shi , J. et al. arXiv arXiv 2017
- Abadi , M. , Barham , P. , Chen , J. , Chen , Z. et al. Tensor Flow: A System for Large-Scale Machine Learning OSDI 2016 USA Nov. 2-4 2016