DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Liang-Chieh Chen1, George Papandreou1, Iasonas Kokkinos2, Kevin Murphy1, Alan Yuille3
1Google, Inc, Mountain View, CA#TAB#
2Univ College London, London, UK
3Departments of Cognitive Science and Computer Science, Johns Hopkins University, Baltimore, MD#TAB#

Tóm tắt

Từ khóa


Tài liệu tham khảo

10.1109/TPAMI.2012.231

chen, 2015, Semantic image segmentation with deep convolutional nets and fully connected CRFs, Proc Int Conf Learn Representations

10.1109/CVPR.2015.7298897

10.1109/ICCV.2013.49

10.1007/s11263-008-0202-0

10.1109/CVPR.2010.5540048

10.1109/CVPR.2016.350

10.1109/CVPR.2014.254

10.1109/CVPR.2014.119

everingham, 2014, The PASCAL visual object classes challenge a retrospective, Int J Comput Vis

lempitsky, 2011, Pylon model for semantic segmentation, Proc Advances Neural Inf Process Syst, 1485

10.1109/ICCV.2009.5459248

10.1007/s11263-011-0437-z

he, 2014, Spatial pyramid pooling in deep convolutional networks for visual recognition, Proc Eur Conf Comput Vis, 346

krähenbühl, 2011, Efficient inference in fully connected CRFs with Gaussian edge potentials, Proc Advances Neural Inf Process Syst, 109

10.1109/CVPR.2015.7298642

10.1007/s11263-007-0109-1

10.1145/1186562.1015720

10.1007/978-3-319-45886-1_2

he, 2004, Multiscale conditional random fields for image labeling, Proc IEEE Comput Soc Conf Comput Vis Pattern Recog, 695

badrinarayanan, 2015, Segnet: A deep convolutional encoder-decoder architecture for image segmentation

10.1109/ICCV.2011.6126219

10.1109/CVPR.2015.7298959

dai, 2014, Convolutional feature masking for joint object and stuff segmentation

10.1109/ICCV.2015.179

papandreou, 2015, Weakly- and semi-supervised learning of a DCNN for semantic image segmentation, Proc IEEE Int Conf Comput Vis, 1742

bell, 2014, Material recognition in the wild with the materials in context database

10.1016/j.neucom.2007.11.031

10.1007/BF00115697

10.1109/34.134040

cogswell, 2014, Combining the best of graphical models and convnets for semantic segmentation

eigen, 2014, Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture

lin, 2015, Efficient piecewise training of deep structured models for semantic segmentation

simonyan, 2015, Very deep convolutional networks for large-scale image recognition, Proc Int Conf Learn Representations

sermanet, 2013, OverFeat: Integrated recognition, localization and detection using convolutional networks

10.1109/CVPR.2015.7298636

szegedy, 2014, Going deeper with convolutions

10.1109/CVPR.2014.276

hariharan, 2014, Simultaneous detection and segmentation, Proc Eur Conf Comput Vis, 297

10.1109/CVPR.2014.81

10.1109/ICCV.2015.169

10.1109/TPAMI.2011.231

carreira, 2012, Semantic segmentation with second-order pooling, Proc Eur Conf Comput Vis, 430

10.1007/s11263-013-0620-5

10.1109/CVPR.2014.49

tu, 2010, Auto-context and its application to high-level vision tasks and 3D brain image segmentation, IEEE Trans Pattern Anal Mach Intell, 32, 1744, 10.1109/TPAMI.2009.186

10.1145/2647868.2654889

10.1109/ICCV.2009.5459175

10.1109/CVPR.2008.4587503

liang, 2015, Proposal-free network for instance-level object segmentation

10.1109/ICCV.2011.6126299

hong, 2015, Decoupled deep neural network for semi-supervised semantic segmentation, Proc 28th Int Conf Neural Inf Process Syst, 1495

10.1109/ICCV.2015.209

yu, 2016, Multi-scale context aggregation by dilated convolutions, Proc Int Conf Learn Representations

dai, 2016, R-FCN: Object detection via region-based fully convolutional networks

10.1109/LSP.2005.853048

10.1109/5.52200

10.1007/978-3-319-46466-4_32

chen, 2015, ABC-CNN: An attention based convolutional neural network for visual question answering

10.1109/ICCV.2015.191

10.1109/ICCV.2015.162

10.1109/ICCV.2015.178

10.1109/CVPR.2016.492

chen, 2015, Learning deep structured models, Proc Int Conf Int Conf Mach Learn, 1785

schwing, 2015, Fully connected deep structured networks

10.1007/978-3-319-46478-7_25

10.1145/1964921.1964964

10.1109/ICCV.2015.65

krizhevsky, 2013, ImageNet classification with deep convolutional neural networks, Proc 25th Int Conf Neural Inf Process Syst, 1097

pinheiro, 2014, Weakly supervised semantic segmentation with convolutional networks

10.1109/5.726791

xia, 2015, Zoom better to see clearer: Huamn part segmentation with auto zoom net

he, 2016, Identity mappings in deep residual networks, 10.1007/978-3-319-46493-0_38

wu, 2016, Bridging category-level and instance-level semantic image segmentation

shen, 2016, Fast semantic image segmentation with high order context and guided filtering

arnab, 2015, Higher order potentials in end-to-end trainable conditional random fields

ghiasi, 2016, Laplacian reconstruction and refinement for semantic segmentation, 10.1007/978-3-319-46487-9_32

ronneberger, 2015, U-net: Convolutional networks for biomedical image segmentation, Proc Int Conf Medical Image Comput Comput -Assisted Intervention, 234

10.1109/CVPR.2015.7298788

10.1109/ICCV.2015.184

liang, 2015, Semantic object parsing with local-global long short-term memory

10.1007/978-3-319-46448-0_8

ren, 2015, Faster R-CNN: Towards real-time object detection with region proposal networks, Proc 28th Int Conf Neural Inf Process Syst, 91

he, 2015, Deep residual learning for image recognition

liu, 2015, SSD: Single shot multibox detector

zeiler, 2014, Visualizing and understanding convolutional networks, Proc Eur Conf Comput Vis, 818

10.1109/CVPR.2015.7298965

10.1007/978-3-642-97177-8_28

10.1109/ICIP.2013.6738831

10.1109/78.157290

10.1109/CVPR.2016.396

wu, 2016, High-performance semantic segmentation using very deep fully convolutional networks

kokkinos, 2016, Pushing the boundaries of boundary detection using deep learning, Proc Int Conf Learn Representations

10.1111/j.1467-8659.2009.01645.x

10.1109/CVPR.2006.68

abadi, 2016, Tensorflow: Large-scale machine learning on heterogeneous distributed systems

10.1109/CVPR.2016.422

yan, 2016, Combining the best of convolutional layers and recurrent layers: A hybrid network for semantic segmentation

10.1109/ICCV.2011.6126343

liu, 2015, Parsenet: Looking wider to see better

lin, 2014, Microsoft COCO: Common objects in context, Proc Eur Conf Comput Vis, 740

10.1109/CVPR.2016.351