Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Liang-Chieh Chen,Yukun Zhu,George Papandreou,Florian Schroff,Hartwig Adam +4 more
- pp 833-851
Reads0
Chats0
TLDR
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.Abstract:
Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries. We further explore the Xception model and apply the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network. We demonstrate the effectiveness of the proposed model on PASCAL VOC 2012 and Cityscapes datasets, achieving the test set performance of 89% and 82.1% without any post-processing. Our paper is accompanied with a publicly available reference implementation of the proposed models in Tensorflow at https://github.com/tensorflow/models/tree/master/research/deeplab.read more
Citations
More filters
Book ChapterDOI
Learning Semantic Neural Tree for Human Parsing
TL;DR: Zhang et al. as discussed by the authors designed a semantic neural tree for human parsing, which uses a tree architecture to encode physiological structure of human body, and design a coarse to fine process in a cascade manner to generate accurate results.
Journal ArticleDOI
Deep learning for image inpainting: A survey
TL;DR: A comprehensive overview of recent advances in deep learning-based image inpainting can be found in this paper , where the authors categorize the deep learningbased techniques from multiple perspectives, including in-painting strategies, network structures, and loss functions.
Journal ArticleDOI
MD-Net: A multi-scale dense network for retinal vessel segmentation
TL;DR: Zhang et al. as mentioned in this paper proposed a multi-scale dense network (MD-Net) that can make full use of multiscale information and encoder features for retinal fundus vessel segmentation.
Posted Content
Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks
TL;DR: This work proposes a network consisting of a Dense Feature Extractor (DFE) and a Depth Map Generator (DMG) that can predict depth map in about 15 fps and can preserve better structural details of the scene depth.
Journal ArticleDOI
Automated detection of aggressive and indolent prostate cancer on magnetic resonance imaging.
Arun Seetharaman,Indrani Bhattacharya,Leo C Chen,Christian A. Kunder,Wei Shao,Simon John Christoph Soerensen,Simon John Christoph Soerensen,Jeffrey B. Wang,Nikola C. Teslovich,Richard E. Fan,Pejman Ghanouni,James D. Brooks,Katherine J. To'o,Katherine J. To'o,Geoffrey A. Sonn,Mirabela Rusu +15 more
TL;DR: The Stanford Prostate Cancer Network (SPCNet) as discussed by the authors is a convolutional neural network model, trained to distinguish between aggressive cancer, indolent cancer, and normal tissue on MRI.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Book ChapterDOI
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.