EdgeSegNet: A Compact Network for Semantic Segmentation

In this study, we introduce EdgeSegNet, a compact deep convolutional neural network for the task of semantic segmentation. A human-machine collaborative design strategy is leveraged to create EdgeSegNet, where principled network design prototyping is coupled with machine-driven design exploration to create networks with customized module-level macroarchitecture and microarchitecture designs tailored for the task. Experimental results showed that EdgeSegNet can achieve semantic segmentation accuracy comparable with much larger and computationally complex networks (>20x} smaller model size than RefineNet) as well as achieving an inference speed of ~38.5 FPS on an NVidia Jetson AGX Xavier. As such, the proposed EdgeSegNet is well-suited for low-power edge scenarios.

[1]  Yoshua Bengio,et al.  BinaryConnect: Training Deep Neural Networks with binary weights during propagations , 2015, NIPS.

[2]  Sujith Ravi,et al.  ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections , 2017, ArXiv.

[3]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[4]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Alexander Wong,et al.  SquishedNets: Squishing SqueezeNet further for edge device scenarios via deep evolutionary synthesis , 2017, ArXiv.

[6]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[7]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[8]  Garrison W. Cottrell,et al.  Understanding Convolution for Semantic Segmentation , 2017, 2018 IEEE Winter Conference on Applications of Computer Vision (WACV).

[9]  Alexander Wong,et al.  NetScore: Towards Universal Metrics for Large-Scale Performance Analysis of Deep Neural Networks for Practical On-Device Edge Usage , 2018, ICIAR.

[10]  Wei Wei,et al.  2019 Formatting Instructions for Authors Using LaTeX , 2018 .

[11]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[12]  George Papandreou,et al.  Rethinking Atrous Convolution for Semantic Image Segmentation , 2017, ArXiv.

[13]  Alexander Wong,et al.  NetScore: Towards Universal Metrics for Large-scale Performance Analysis of Deep Neural Networks for Practical Usage , 2018, ArXiv.

[14]  Frank Hutter,et al.  Multi-objective Architecture Search for CNNs , 2018, ArXiv.

[15]  Ming Zhang,et al.  Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices , 2017, ArXiv.

[16]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[17]  Alexander Wong,et al.  Tiny SSD: A Tiny Single-Shot Detection Deep Convolutional Neural Network for Real-Time Embedded Object Detection , 2018, 2018 15th Conference on Computer and Robot Vision (CRV).

[18]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[20]  Alexander Wong,et al.  FermiNets: Learning generative machines to generate efficient neural networks via generative synthesis , 2018, ArXiv.

[21]  Bo Chen,et al.  MnasNet: Platform-Aware Neural Architecture Search for Mobile , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[23]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Xiangyu Zhang,et al.  ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[25]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[26]  Bo Chen,et al.  Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[27]  Roberto Cipolla,et al.  Semantic object classes in video: A high-definition ground truth database , 2009, Pattern Recognit. Lett..

[28]  Alexander Wong,et al.  AttoNets: Compact and Efficient Deep Neural Networks for the Edge via Human-Machine Collaborative Design , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[29]  Ian D. Reid,et al.  RefineNet : MultiPath Refinement Networks with Identity Mappings for High-Resolution Semantic Segmentation , 2016 .

[30]  Xiangyu Zhang,et al.  ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design , 2018, ECCV.