CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

PDF papers
References
id acadia18_166
authors Kvochick, Tyler
year 2018
title Sneaky Spatial Segmentation. Reading Architectural Drawings with Deep Neural Networks and Without Labeling Data
source ACADIA // 2018: Recalibration. On imprecisionand infidelity. [Proceedings of the 38th Annual Conference of the Association for Computer Aided Design in Architecture (ACADIA) ISBN 978-0-692-17729-7] Mexico City, Mexico 18-20 October, 2018, pp. 166-175
summary Currently, it is nearly impossible for an artificial neural network to generalize a task from very few examples. Humans, however, excel at this. For instance, it is not necessary for a designer to see thousands or millions of unique examples of how to place a given drawing symbol in a way that meets the economic, aesthetic, and performative goals of the project. In fact, the goals can be (and usually are) communicated abstractly in natural language. Machine learning (ML) models, however, do need numerous examples. The methods that we explore here are an attempt to circumvent this in order to make ML models more immediately useful.

In this work, we present progress on the application of contemporary ML techniques to the design process in the architecture, engineering, and construction (AEC) industry. We introduce a technique to partially circumvent the data hungriness of neural networks, which is a significant impediment to their application outside of the ML research community. We also show results on the applicability of this technique to real-world drawings and present research that addresses how some fundamental attributes of drawings as images affect the way they are interpreted in deep neural networks. Our primary contribution is a technique to train a neural network to segment real-world architectural drawings after using only generated pseudodrawings.

keywords full paper, representation + perception, computation, ai & machine learning
series ACADIA
type paper
email tyler.kvochick@teecom.com
full text file.pdf (6,787,633 bytes)
references Content-type: text/plain
Details Citation Select
100%; open American Institute of Architects, The (2016) Find in CUMINCAD Architectural Graphic Standards, 12th ed, edited by Dennis J. Hall. Hoboken , NJ: John Wiley & Sons. https://www.graphicstandards.com/

100%; open Caley, Jeffrey A., Nicholas R.J. Lawrance, and Geoffrey A. Hollinger (2016) Find in CUMINCAD Deep Learning of Structured Environments for Robot Search , Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 3987–92. Daejeon, Korea: IROS. doi:10.1109/IROS.2016.7759587

100%; open Dai, Jifeng, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, and Yichen Wei (2017) Find in CUMINCAD Deformable Convolutional Networks , ArXiv:1703.06211 [Cs], March. http://arxiv.org/abs/1703.06211

100%; open Denton, Emily, Soumith Chintala, Arthur Szlam, and Rob Fergus (2015) Find in CUMINCAD Deep Generative Image Models Using a Laplacian Pyramid of Adversarial Networks , ArXiv:1506.05751 [Cs], June. http://arxiv.org/abs/1506.05751

100%; open Dodge, Samuel, Jiu Xu, and Bjorn Stenger (2017) Find in CUMINCAD Parsing Floor Plan Images , Proceedings of the Fifteenth IAPR International Conference on Machine Vision Applications, 358–61. Nagoya, Japan: MVA. doi:10.23919/MVA.2017.7986875

100%; open Jain, Sambhav R., and Kye Okabe (2017) Find in CUMINCAD Training a Fully Convolutional Neural Network to Route Integrated Circuits , June. https://arxiv.org/abs/1706.08948

100%; open Kingma, Diederik P., and Jimmy Ba (2014) Find in CUMINCAD Adam: A Method for Stochastic Optimization , December. https://arxiv.org/abs/1412.6980

100%; open Leal-Taixé, Laura, Anton Milan, Ian Reid, Stefan Roth, and Konrad Schindler (2015) Find in CUMINCAD MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking , April. https://arxiv.org/abs/1504.01942

100%; open Lin, Tsung-Yi, Michael Maire, Serge Belongie, Lubomir Bourdev, Ross Girshick, James Hays, Pietro Perona, Deva Ramanan, C. Lawrence Zitnick, and Piotr Dollár (2014) Find in CUMINCAD Microsoft COCO: Common Objects in Context , ArXiv:1405.0312 [Cs], May. http://arxiv.org/abs/1405.0312

100%; open Masters, Dominic, and Carlo Luschi (2018) Find in CUMINCAD Revisiting Small Batch Training for Deep Neural Networks , ArXiv:1804.07612 [Cs, Stat], April. http://arxiv.org/abs/1804.07612

100%; open Miikkulainen, Risto, Jason Liang, Elliot Meyerson, Aditya Rawal, Dan Fink, Olivier Francon, Bala Raju, et al. (2017) Find in CUMINCAD Evolving Deep Neural Networks , ArXiv:1703.00548 [Cs], March. http://arxiv.org/abs/1703.00548

100%; open Orhan, A. Emin, and Xaq Pitkow (2017) Find in CUMINCAD Skip Connections Eliminate Singularities , ArXiv:1701.09175 [Cs], January. http://arxiv.org/abs/1701.09175

100%; open Perez, Luis, and Jason Wang (2017) Find in CUMINCAD The Effectiveness of Data Augmentation in Image Classification Using Deep Learning , ArXiv:1712.04621 [Cs], December. http://arxiv.org/abs/1712.04621

100%; open Rahman, Md Atiqur, and Yang Wang (2016) Find in CUMINCAD Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation , Advances in Visual Computing: Proceedings of the 12th International Symposium on Visual Computing, edited by G. Bebis, R. Boyle, B. Parvin, D. Koracin, F. Porikli, S. Skaff, Al. Entezari, et al., 10072: 234–44. Cham: Springer International Publishing. doi:10.1007/978-3-319-50835-1_22

100%; open Russakovsky, Olga, Jia Deng, Zhiheng Huang, Alexander C. Berg, and Li Fei-Fei (2013) Find in CUMINCAD Detecting Avocados to Zucchinis: What Have We Done, and Where Are We Going? , Proceedings of the IEEE International Conference on Computer Vision, 2064–71. Sydney, Australia: ICCV. doi:10.1109/ICCV.2013.258

100%; open Shelhamer, Evan, Jonathan Long, and Trevor Darrell (2016) Find in CUMINCAD Fully Convolutional Networks for Semantic Segmentation , ArXiv:1605.06211 [Cs], May. http://arxiv.org/abs/1605.06211

100%; open Tyleček, Radim, and Radim Šára (2013) Find in CUMINCAD Spatial Pattern Templates for Recognition of Objects with Regular Structure , Pattern Recognition: 35th German Conference on Pattern Recognition, edited by Joachim Weickert, Matthias Hein, and Bernt Schiele, 8142: 364–74. Berlin: Springer. doi:10.1007/978-3-642-40602-7_39

100%; open Wang, Xiaosong, Yifan Peng, Le Lu, Zhiyong Lu, Mohammadhadi Bagheri, and Ronald M. Summers (2017) Find in CUMINCAD ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases , Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3462–71. Honolulu, HI: CVPR. doi:10.1109/CVPR.2017.369

100%; open Zhang, Mengxiao, Wangquan Wu, Yanren Zhang, Kun He, Tao Yu, Huan Long, and John E. Hopcroft (2017) Find in CUMINCAD The Local Dimension of Deep Manifold , November. https://arxiv.org/abs/1711.01573

last changed 2019/01/07 11:21
pick and add to favorite papersHOMELOGIN (you are user _anon_921113 from group guest) CUMINCAD Papers Powered by SciX Open Publishing Services 1.002