Fully Convolutional Networks for Semantic Segmentation

Evan Shelhamer1, Jonathan Long1, Trevor Darrell1
1Department of Electrical Engineering and Computer Science (CS Division), University of California, Berkeley, CA, USA.

Tóm tắt

Từ khóa


Tài liệu tham khảo

chen, 0, Semantic image segmentation with deep convolutional nets and fully connected CRFs, Proc Int Conf Learn Represent

hong, 0, Decoupled deep neural network for semi-supervised semantic segmentation, Proc Neural Inf Process Syst, 1495

10.1109/TPAMI.2015.2505283

10.1109/ICCV.2015.164

10.1109/TPAMI.2016.2577031

10.1109/CVPR.2015.7298959

10.1109/ICCV.2015.191

papandreou, 0, Weakly-and semi-supervised learning of a DCNN for semantic image segmentation, Proc Int Conf Comput Vis, 1742

10.1109/ICCV.2015.209

fischer, 0, Learning optical flow with convolutional networks, Proc Int Conf Comput Vis

10.1109/CVPR.2015.7299025

10.1109/CVPR.2014.119

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

10.1109/CVPR.2013.465

10.1007/BF00318371

10.1109/CVPR.2015.7298642

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

10.1145/3065386

matan, 0, Multi-digit recognition using a space displacement neural network, Proc Neural Inf Process Syst, 488

wolf, 0, Postal address block location using a convolutional locator network, Proc Neural Inf Process Syst, 745

lecun, 0, Backpropagation applied to hand-written zip code recognition, Proc Neural Comput, 541

tompson, 0, Joint training of a convolutional network and a graphical model for human pose estimation, Proc Neural Inf Process Syst, 1799

10.1109/ICCV.2013.84

10.1109/TCOM.1983.1095851

eigen, 0, Depth map prediction from a single image using a multi-scale deep network, Proc Neural Inf Process Syst, 2366

everingham, 0, The PASCAL Visual Object Classes Challenge 2011 Results

bishop, 2006, Pattern Recognition and Machine Learning, 229

10.1109/CVPR.2013.386

10.1007/s11263-012-0574-z

10.1109/TPAMI.2010.147

10.1109/CVPR.2013.79

silberman, 0, Indoor segmentation and support inference from RGBD images, Proc Eur Conf Comput Vis, 746

10.1145/2647868.2654889

lecun, 0, Efficient backprop, Neural Networks Tricks of the Trade, 9

10.1109/ICCV.2011.6126343

10.1109/TIP.2005.852470

ciresan, 0, Deep neural networks segment neuronal membranes in electron microscopy images, Proc Neural Inf Process Syst, 2852

10.1109/ICCV.2015.179

10.1109/TPAMI.2012.231

pinheiro, 0, Recurrent convolutional neural networks for scene labeling, Proc 31st Int Conf Mach Learn, 82

hariharan, 0, Simultaneous detection and segmentation, Proc Eur Conf Comput Vis, 297

gupta, 0, Learning rich features from RGB-D images for object detection and segmentation, Proc Eur Conf Comput Vis, 345

ganin, 0, N$^4$ -fields: Neural network nearest neighbor fields for image transforms, Proc Asian Conf Comput Vis, 536

10.1109/CVPR.2015.7298965

donahue, 0, DeCAF: A deep convolutional activation feature for generic visual recognition, Proc Int Conf Mach Learn, 647

zeiler, 0, Visualizing and understanding convolutional networks, Proc Eur Conf Comput Vis, 818

sermanet, 0, OverFeat: Integrated recognition, localization and detection using convolutional networks, Proc Int Conf Learn Represent

10.1109/CVPR.2015.7298594

he, 0, Spatial pyramid pooling in deep convolutional networks for visual recognition, Proc Eur Conf Comput Vis, 346

10.1109/TPAMI.2015.2437384

long, 0, Do convnets learn correspondence?, Proc Neural Inf Process Syst, 1601

zhang, 0, Part-based R-CNNs for fine-grained category detection, Proc Eur Conf Comput Vis, 834

wan, 0, Regularization of neural networks using DropConnect, Proc Int Conf Mach Learn, 1058

fischer, 0, Descriptor matching with convolutional neural networks: A comparison to SIFT, arXiv preprint arXiv 1405 5769

holschneider, 0, A real-time algorithm for signal analysis with the help of the wavelet transform, Proc Int Conf Time-Freq Methods Phase Space, 286

10.1109/ICIP.2013.6738831

10.1109/5.52200

mallat, 1999, A Wavelet Tour of Signal Processing

10.1109/ICCV.2015.178

liu, 0, ParseNet: Looking wider to see better

yu, 0, Multi-scale context aggregation by dilated convolutions, Proc Int Conf Learn Represent

ronneberger, 0, U-Net: Convolutional networks for biomedical image segmentation, Proc Med Image Comput Comput -Assist Intervention, 234