CompositeTasking: Understanding Images by Spatial Composition of Tasks.
作者： Danda Pani Paudel , Luc Van Gool , Nikola Popovic , Thomas Probst , Guolei Sun
DOI:
关键词: Artificial intelligence 、 Source code 、 Set (abstract data type) 、 Pattern recognition 、 Composition (combinatorics) 、 Task (computing) 、 Image (mathematics) 、 Computer science
摘要: We define the concept of CompositeTasking as fusion multiple, spatially distributed tasks, for various aspects image understanding. Learning to perform tasks is motivated by frequent availability only sparse labels across and desire a compact multi-tasking network. To facilitate CompositeTasking, we introduce novel task conditioning model -- single encoder-decoder network that performs varying at once. The proposed takes pair an set pixel-wise dense inputs, makes related predictions each pixel, which includes decision applying where. As latter, learn composition needs be performed according some rules. It not offers us multi-tasking, but also allows task-editing. strength method demonstrated having supply supervision per task. obtained results are on par with our baselines use multi-headed design. source code will made publicly available www.github.com/nikola3794/composite-tasking .
arxiv.org参考文章(56)
Philipp Fischer, Thomas Brox, None, U-Net: Convolutional Networks for Biomedical Image Segmentation medical image computing and computer assisted intervention. pp. 234- 241 ,(2015) , 10.1007/978-3-319-24574-4_28
Federica Bogo, Javier Romero, Matthew Loper, Michael J. Black, FAUST: Dataset and Evaluation for 3D Mesh Registration computer vision and pattern recognition. pp. 3794- 3801 ,(2014) , 10.1109/CVPR.2014.491
Mark Everingham, Luc Van Gool, Christopher K. I. Williams, John Winn, Andrew Zisserman, The Pascal Visual Object Classes (VOC) Challenge International Journal of Computer Vision. ,vol. 88, pp. 303- 338 ,(2010) , 10.1007/S11263-009-0275-4
Hamed Pirsiavash, Antonio Torralba, Joseph Jaewhan Lim, None, Parsing IKEA Objects: Fine Pose Estimation international conference on computer vision. pp. 2992- 2999 ,(2013) , 10.1109/ICCV.2013.372
Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, Li Fei-Fei, ImageNet Large Scale Visual Recognition Challenge International Journal of Computer Vision. ,vol. 115, pp. 211- 252 ,(2015) , 10.1007/S11263-015-0816-Y
D.R. Martin, C.C. Fowlkes, J. Malik, Learning to detect natural image boundaries using local brightness, color, and texture cues IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 26, pp. 530- 549 ,(2004) , 10.1109/TPAMI.2004.1273918
Roozbeh Mottaghi, Xianjie Chen, Xiaobai Liu, Nam-Gyu Cho, Seong-Whan Lee, Sanja Fidler, Raquel Urtasun, Alan Yuille, The Role of Context for Object Detection and Semantic Segmentation in the Wild computer vision and pattern recognition. pp. 891- 898 ,(2014) , 10.1109/CVPR.2014.119
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep Residual Learning for Image Recognition computer vision and pattern recognition. pp. 770- 778 ,(2016) , 10.1109/CVPR.2016.90
Zhenqi Xu, Shan Li, Weihong Deng, Learning temporal features using LSTM-CNN architecture for face anti-spoofing 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR). pp. 141- 145 ,(2015) , 10.1109/ACPR.2015.7486482
Andrea Vedaldi, Victor S. Lempitsky, Dmitry Ulyanov, Instance Normalization: The Missing Ingredient for Fast Stylization. arXiv: Computer Vision and Pattern Recognition. ,(2016)