Corpus ID: 150373855

EdgeSegNet: A Compact Network for Semantic Segmentation

  title={EdgeSegNet: A Compact Network for Semantic Segmentation},
  author={Z. Lin and Brendan Chwyl and A. Wong},
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… Expand
AttendSeg: A Tiny Attention Condenser Neural Network for Semantic Segmentation on the Edge
Experimental results demonstrated that the proposed AttendSeg can achieve segmentation accuracy comparable to much larger deep neural networks with greater complexity while possessing a significantly lower architecture and computational complexity, making it well-suited for TinyML applications on the edge. Expand
AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers
Low-precision, highly compact deep neural networks tailored for on-device image recognition, which possesses deep self-attention architectures based on visual attention condensers, which extends on the recently introduced stand-alone attention Condensers to improve spatial-channel selective attention are introduced. Expand
Highly Efficient Deep Intelligence via Multi-Parent Evolutionary Synthesis of Deep Neural Networks
A general framework for synthesizing efficient neural network architectures via multi-parent evolutionary synthesis is introduced, generalized from the asexual evolutionary synthesis approach, and allows for a newly synthesized network to be dependent on a subset of all previously synthesized networks. Expand
Benchmarking Jetson Platform for 3D Point-Cloud and Hyper-Spectral Image Classification
  • Shan Ullah, Deok-Hwan Kim
  • Computer Science
  • 2020 IEEE International Conference on Big Data and Smart Computing (BigComp)
  • 2020
This paper presents benchmarking of Jetson platforms (Nano, TX1, and Xavier) by evaluating its performance based on computationally expensive deep learning algorithms and presents the detailed evaluation exclusively in term of performance indices as inference time, the maximum number of concurrent processes, resource utilization per process and efficiency. Expand
Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU
This paper proposes a novel training methodology to train and scale the existing semantic segmentation models for a large number of semantic classes without increasing the memory overhead, and proposes an approximation method for ground-truth class probability, and uses it to compute cross-entropy loss. Expand


RefineNet : MultiPath Refinement Networks with Identity Mappings for High-Resolution Semantic Segmentation
RefineNet is presented, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections and introduces chained residual pooling, which captures rich background context in an efficient manner. Expand
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
This work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs, and derives several practical guidelines for efficient network design, called ShuffleNet V2. Expand
Understanding Convolution for Semantic Segmentation
DUC is designed to generate pixel-level prediction, which is able to capture and decode more detailed information that is generally missing in bilinear upsampling, and a hybrid dilated convolution (HDC) framework in the encoding phase is proposed. Expand
Rethinking Atrous Convolution for Semantic Image Segmentation
The proposed `DeepLabv3' system significantly improves over the previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark. Expand
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. Expand
MobileNetV2: Inverted Residuals and Linear Bottlenecks
A new mobile architecture, MobileNetV2, is described that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes and allows decoupling of the input/output domains from the expressiveness of the transformation. Expand
Pyramid Scene Parsing Network
This paper exploits the capability of global context information by different-region-based context aggregation through the pyramid pooling module together with the proposed pyramid scene parsing network (PSPNet) to produce good quality results on the scene parsing task. Expand
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
This work extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries and applies the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network. Expand
AttoNets: Compact and Efficient Deep Neural Networks for the Edge via Human-Machine Collaborative Design
  • A. Wong, Z. Lin, Brendan Chwyl
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2019
This study takes a deeper exploration into a human-machine collaborative design approach for creating highly efficient deep neural networks through a synergy between principled network design prototyping and machine-driven design exploration. Expand
MnasNet: Platform-Aware Neural Architecture Search for Mobile
An automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. Expand