Publication
PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing
This work explores unbiased point-cloud classification and provides a tool for interpretability (debugging) deep point-cloud networks. The method enables a user to see which variables (parts/points) in the input contribute most to a final prediction.
Download publicationAbstract
PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing
Saeid Asgari Taghanaki, Kaveh Hassani, Pradeep Kumar Jayaraman, Amir Hosein Khasahmadi, Tonya Custis
International Conference on Machine Learning 2020
Deep classifiers tend to associate a few discriminative input variables with their objective function, which in turn, may hurt their generalization capabilities. To address this, one can design systematic experiments and/or inspect the models via interpretability methods. In this paper, we investigate both of these strategies on deep models operating on point clouds. We propose PointMask, a model-agnostic interpretable information-bottleneck approach for attribution in point cloud models. PointMask encourages exploring the majority of variation factors in the input space while gradually converging to a general solution. More specifically, PointMask introduces a regularization term that minimizes the mutual information between the input and the latent features used to masks out irrelevant variables. We show that coupling a PointMask layer with an arbitrary model can discern the points in the input space which contribute the most to the prediction score, thereby leading to interpretability. Through designed bias experiments, we also show that thanks to its gradual masking feature, our proposed method is effective in handling data bias.
Related Resources
2023
Hierarchical Neural Coding for Controllable CAD Model Generation
This paper presents a new controllable parametric CAD generative…
2021
Neural UpFlow: A Scene Flow Learning Approach to Increase the Apparent Resolution of Particle-Based Liquids
In this research, we introduce a data-driven approach to increase the…
2020
Learning to Simulate and Design for Structural Engineering
The structural design process for buildings is time consuming and…
2019
Dynamic Experience Replay
We present a novel technique called Dynamic Experience Replay (DER)…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us