Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud

Authors: Yachao Zhang, Zonghao Li, Yuan Xie, Yanyun Qu, Cuihua Li, Tao Mei3421-3429

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our method is evaluated on large-scale point cloud datasets with different scenarios including indoor and outdoor. The experimental results show the large gain against existing weakly supervised methods and comparable results to fully supervised methods.
Researcher Affiliation Collaboration Yachao Zhang1, Zonghao Li1, Yuan Xie2 , Yanyun Qu1 , Cuihua Li1, Tao Mei3 1 School of Informatics, Xiamen University, Fujian, China 2 School of Computer Science and Technology, East China Normal University, Shanghai, China 3 JD AI Research, Beijing, China
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 choose Scan Net (Dai et al. 2017) as the pre-training dataset...we experiment on the indoor scene dataset S3DIS (Armeni et al. 2016) and Scan Netv2 (Dai et al. 2017) and outdoor dataset Semantic3D (Hackel et al. 2017).
Dataset Splits Yes We conduct a pilot study to understand the effectiveness and show the m Io U curve of our method and baseline on validation set.
Hardware Specification Yes The two networks can be trained built upon Tensor Flow with a single NVIDIA Titan RTX.
Software Dependencies No The paper mentions 'Tensor Flow' but does not provide a specific version number or other software dependencies with versions.
Experiment Setup Yes We use Adam optimizer with default parameters. The number of neighboring points K is 16. Both the self-supervised pretext task and weakly semantic segmentation network are trained 80 epochs.