1 Hit in 1.7 sec

PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing [article]

Saeid Asgari Taghanaki, Kaveh Hassani, Pradeep Kumar Jayaraman, Amir Hosein Khasahmadi, Tonya Custis
2020 arXiv   pre-print
We propose PointMask, a model-agnostic interpretable information-bottleneck approach for attribution in point cloud models.  ...  In this paper, we investigate both of these strategies on deep models operating on point clouds.  ...  Acknowledgements We would like to thank Aditya Sanghi and Ara Danielyan for their useful input through the course of this research.  ... 
arXiv:2007.04525v1 fatcat:2amdw43p2nf2lou7iupu35w4o4