A Deeper Look at 3D Shape Classifiers

Understand

We investigate the role of representations and architectures for classifying 3D shapes in terms of their computational efficiency, generalization, and robustness to adversarial transformations.

• By varying the number of training examples and employing cross-modal transfer learning we study the role of initialization of existing deep architectures for 3D shape classification.
• Our analysis shows that multiview methods continue to offer the best generalization even without pretraining on large labeled image datasets, and even when trained on simplified inputs such as binary silhouettes.
• Furthermore, the performance of voxel-based 3D convolutional networks and point-based architectures can be improved via cross-modal transfer from image representations.