REVIEW 2 cited by
PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 2 Pith papers
-
XAI for Point Cloud Data using Perturbations based on Meaningful Segmentation
A new XAI method for point cloud classification uses semantic segmentation to define meaningful perturbation regions and a point-shifting mechanism to compute saliency maps.
-
Learning Causality for Modern Machine Learning
A thesis compiling six papers that use causal invariance to improve graph neural networks' out-of-distribution generalization, interpretability, and robustness.
Discussion (0). Sign in to comment.