RobustPointSet

This paper shows how almost all the deep learning-based point cloud classifiers fail when test data is transformed with simple common data corruptions. It also proposes a dataset for analyzing the robustness of point cloud classifiers.

Abstract

RobustPointSet: A Dataset for Benchmarking Robustness of Point Cloud Classifiers

Saeid Asgari Taghanaki, Jieliang Luo, Ran Zhang, Ye Wang, Pradeep Kumar Jayaraman, Krishna Murthy Jatavallabhula

“Robust and Reliable Machine Learning in the Real World Workshop”; (RobustML), ICLR 2021

The 3D deep learning community has seen significant strides in pointcloud processing over the last few years. However, the datasets on which deep models have been trained have largely remained the same. Most datasets comprise clean, clutter-free pointclouds canonicalized for pose. Models trained on these datasets fail in uninterpretible and unintuitive ways when presented with data that contains transformations u0022unseenu0022 at train time. While data augmentation enables models to be robust to u0022previously seenu0022 input transformations, 1) we show that this does not work for unseen transformations during inference, and 2) data augmentation makes it difficult to analyze a model’s inherent robustness to transformations. To this end, we create a publicly available dataset for robustness analysis of point cloud classification models (independent of data augmentation) to input transformations, called RobustPointSet. Our experiments indicate that despite all the progress in the point cloud classification, there is no single architecture that consistently performs better u002du002d several fail drastically u002du002d when evaluated on transformed test sets. We also find that robustness to unseen transformations cannot be brought about merely by extensive data augmentation.