DeepFacade: A Deep Learning Approach to Facade Parsing

Authors: Hantang Liu, Jialiang Zhang, Jianke Zhu, Steven C. H. Hoi

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We test our method by training a FCN-8s network with the novel loss function. Experimental results show that our method has outperformed previous state-of-the-art methods significantly on both the ECP dataset and the e TRIMS dataset.
Researcher Affiliation Collaboration 1 College of Computer Science, Zhejiang University, China 2Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies 3School of Information Systems, Singapore Management University, Singapore
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes We evaluate our porposed approach on two different datasets, the Ecole Centrale Paris (ECP) Facades dataset [Teboul et al., 2010] and the e TRIMS [Korˇc and Förstner, 2009] database.
Dataset Splits Yes 5-fold cross-validation is taken to generate proposals from all images.
Hardware Specification No The paper does not provide specific hardware details used for running its experiments.
Software Dependencies No The paper mentions software components like 'VGG16', 'Faster R-CNN', 'RPN', and 'Adam optimizer' but does not provide specific version numbers for any of them.
Experiment Setup Yes The initial learning rate is set to 10 6. For the ECP dataset, training epoch is 100 and for the e TRIMS dataset training epoch is 80. ... Dropout [Srivastava et al., 2014] is used during training to prevent overfitting. ... For η in Equation 8, we set it to be 0.17 empirically.