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
Proceedings ArticleDOI
CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency
TL;DR: Zhang et al. as discussed by the authors proposed CAMERAS, a technique to compute high-fidelity backpropagation saliency maps without requiring any external priors and preserving the map sanity.
Proceedings ArticleDOI
ARTHuS: Adaptive Real-Time Human Segmentation in Sports Through Online Distillation
Anthony Cioppa,Adrien Deliège,Maxime Istasse,Christophe De Vleeschouwer,Marc Van Droogenbroeck +4 more
TL;DR: This work develops a general method, named ARTHuS, that produces adaptive real-time match-specific networks for human segmentation in sports videos, without requiring any manual annotation.
Journal ArticleDOI
MANet: a multi-level aggregation network for semantic segmentation of high-resolution remote sensing images
TL;DR: In this article , a multi-level aggregation network (MANet) is proposed to extract deep global features by learning the interrelationships of all positions in the context, and filters redundant channel information as well.
Journal ArticleDOI
Cloud/shadow segmentation based on multi-level feature enhanced network for remote sensing imagery
TL;DR: Wang et al. as discussed by the authors proposed a multilevel feature enhanced network for cloud/shadow segmentation, where ResNet-18 is used as the backbone to extract all levels of semantic information, and Feature Enhancement Module is proposed to strengthen the feature information to obtain more effective feature information.
Proceedings ArticleDOI
Heimdall: mobile GPU coordination platform for augmented reality applications
Juheon Yi,Youngki Lee +1 more
TL;DR: Heimdall, a mobile GPU coordination platform for emerging Augmented Reality (AR) applications, is presented with a Pseudo-Preemption mechanism which breaks down the bulky DNN into smaller units, and prioritizes and flexibly schedules concurrent GPU tasks.
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.