Unsupervised Multi-Task Feature Learning on Point Clouds

Add to your list(s) Download to your calendar using vCal

• Hooman Shayani -- Autodesk
• Thursday 28 November 2019, 13:00-14:30
• Kavli Large Meeting Room, Kavli Building.

If you have a question about this talk, please contact James Fergusson.

We introduce an unsupervised multi-task model to jointly learn point and shape features on point clouds. We define three unsupervised tasks including clustering, reconstruction, and self-supervised classification to train a multi-scale graph-based encoder. We evaluate our model on shape classification and segmentation benchmarks. The results suggest that it outperforms prior state-of-the-art unsupervised models: In the ModelNet40 classification task, it achieves an accuracy of 89.1% and in ShapeNet segmentation task, it achieves an mIoU of 68.2 and accuracy of 88.6%. (based on: https://arxiv.org/pdf/1910.08207.pdf)

This talk is part of the Data Intensive Science Seminar Series series.

This talk is included in these lists:

• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Combined External Astrophysics Talks DAMTP
• Cosmology, Astrophysics and General Relativity
• Institute of Astronomy Extra Talks
• Institute of Astronomy Talk Lists
• Interested Talks
• Kavli Large Meeting Room, Kavli Building
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.