| id |
ecaade2021_254 |
| authors |
Eisenstadt, Viktor, Arora, Hardik, Ziegler, Christoph, Bielski, Jessica, Langenhan, Christoph, Althoff, Klaus-Dieter and Dengel, Andreas |
| year |
2021 |
| title |
Comparative Evaluation of Tensor-based Data Representations for Deep Learning Methods in Architecture |
| source |
Stojakovic, V and Tepavcevic, B (eds.), Towards a new, configurable architecture - Proceedings of the 39th eCAADe Conference - Volume 1, University of Novi Sad, Novi Sad, Serbia, 8-10 September 2021, pp. 45-54 |
| doi |
https://doi.org/10.52842/conf.ecaade.2021.1.045
|
| summary |
This paper presents an extended evaluation of tensor-based representations of graph-based architectural room configurations. This experiment is a continuation of examination of recognition of semantic architectural features by contemporary standard deep learning methods. The main aim of this evaluation is to investigate how the deep learning models trained using the relation tensors as data representation means perform on data not available in the training dataset. Using a straightforward classification task, stepwise modifications of the original training dataset and manually created spatial configurations were fed into the models to measure their prediction quality. We hypothesized that the modifications that influence the class label will not decrease this quality, however, this was not confirmed and most likely the latent non-class defining features make up the class for the model. Under specific circumstances, the prediction quality still remained high for the winning relation tensor type. |
| keywords |
Deep Learning; Spatial Configuration; Semantic Building Fingerprint |
| series |
eCAADe |
| email |
|
| full text |
 file.pdf (838,437 bytes) |
| references |
Content-type: text/plain
|
Arora, H, Langenhan, C, Petzold, F, Eisenstadt, V and Althoff, KD (2020)
 METIS-GAN: An approach to generate spatial configurations using deep learning and semantic building models
, ECPPM 2020-2021
|
|
|
|
|
de Miguel, J (2019)
Deep Form Finding-Using Variational Autoencoders for deep form finding of structural typologies
, eCAADeSIGraDi 2019
|
|
|
|
|
Eisenstadt, V, Arora, H, Ziegler, C, Bielski, J, Langenhan, C, Althoff, KD and Dengel, A (2021)
Exploring optimal ways to represent topological and spatial features of building designs in deep learning methods and applications for architecture
, CAADRIA 2021
|
|
|
|
|
Eisenstadt, V, Langenhan, C, Althoff, KD and Dengel, A (2020)
Improved and Visually Enhanced Case-Based Retrieval of Room Configurations for Assistance in Architectural Design Education
, ICCBR 2020
|
|
|
|
|
Hickman, G. and Krolik, J.L. (2009)
A graph-theoretic approach to constrained floor plan estimation from radar measurements
, IEEE transactions on signal processing, 57(5), pp. 1877-1888
|
|
|
|
|
Newton, D (2019)
Deep Generative Learning for the Generation and Analysis of Architectural Plans with Small Datasets
, eCAADeSIGraDi 2019
|
|
|
|
|
Sharma, D, Gupta, N, Chattopadhyay, C and Mehta, S (2017)
DANIEL: A deep architecture for automatic analysis and retrieval of building floor plans
, 14th IAPR ICDAR, pp. 420-425
|
|
|
|
|
Silvestre, J and Ikeda, Y (2016)
Artificial imagination of architecture with deep convolutional neural network
, CAADRIA 2016
|
|
|
|
|
Steadman, P and Mitchell, LJ (2010)
Architectural morphospace: mapping worlds of built forms
, Environment and Planning B: Planning and Design, 37(2), pp. 197-220
|
|
|
|
|
Sun, C, Hsiao, CW, Sun, M and Chen, HT (2019)
Horizonnet: Learning room layout with 1d representation and pano stretch data augmentation
, IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1047-1056
|
|
|
|
|
Wang, M, Yu, L, Zheng, D, Gan, Q, Gai, Y and Ye, Z (2019)
Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs
, arXiv:1909.01315
|
|
|
|
| last changed |
2022/06/07 07:55 |
|
