Unsupervised Classification of Street Architectures Based on InfoGAN
| Autor: | Yi Zheng, Ziran Liao, Renjie Xie, Junyan Yang, Xianhan Zeng, Zefei Gao, Ning Wang, Qiao Wang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
business.industry Heuristic Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition Machine learning computer.software_genre Image (mathematics) Classifier (linguistics) Labeled data Artificial intelligence business computer Generative grammar |
| Popis: | Street architectures play an essential role in city image and streetscape analysing. However, existing approaches are all supervised which require costly labeled data. To solve this, we propose a street architectural unsupervised classification framework based on Information maximizing Generative Adversarial Nets (InfoGAN), in which we utilize the auxiliary distribution $Q$ of InfoGAN as an unsupervised classifier. Experiments on database of true street view images in Nanjing, China validate the practicality and accuracy of our framework. Furthermore, we draw a series of heuristic conclusions from the intrinsic information hidden in true images. These conclusions will assist planners to know the architectural categories better. arXiv admin note: text overlap with arXiv:1804.08286, arXiv:1606.03657 by other authors |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|