AI Paper Atlas

Research map / Point clouds / Point cloud classification

Interpreting Representation Quality of DNNs for 3D Point Cloud Processing

Wen Shen, Qihan Ren, Dongrui Liu, Quanshi Zhang

NeurIPS 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
adversarially train GCNN with rotation and translation attacks (ablation)GCNN · ModelNet10rotation sensitivity: 0.174{ $\pm$0.067} -> 0.034{ $\pm$0.012}Improved
add translation data augmentation (ablation)PointNet and DGCNN · ModelNet10translation sensitivity: PointNet: 0.160{ $\pm$0.067} -> 0.111{ $\pm$ 0.053}; DGCNN: 0.098{ $\pm$0.054} -> 0.048{ $\pm$ 0.024}Improved
add scale data augmentation (ablation)PointNet and DGCNN · ModelNet10scale sensitivity: PointNet: 0.063{ $\pm$0.047} -> 0.025{ $\pm$0.017}; DGCNN: 0.028{ $\pm$0.020} -> 0.020{ $\pm$0.015}Improved
add y-axis rotation augmentation (ablation)PointNet and DGCNN · ModelNet10rotation sensitivity: PointNet: 0.155{ $\pm$0.068} -> 0.108{ $\pm$0.047}; DGCNN: 0.173{ $\pm$0.072} -> 0.158{ $\pm$0.063}Improved
add random-axis rotation augmentation (ablation)PointNet and DGCNN · ModelNet10rotation sensitivity: PointNet: 0.155{ $\pm$0.068} -> 0.057{ $\pm$0.030}; DGCNN: 0.173{ $\pm$0.072} -> 0.052{ $\pm$0.021}Improved
use rotation-based adversarial training rather than random-axis rotation augmentation (ablation)DGCNN and GCNN · ModelNet10rotation sensitivity: DGCNN: 0.052 { $\pm$0.021} -> 0.036{ $\pm$0.015}; GCNN: 0.048{ $\pm$0.024} -> 0.028{ $\pm$0.016}Improved
adversarially train GCNN with rotation and translation attacks (ablation)GCNN · ModelNet10accuracy: 95.1 -> 91.0Hurt
adversarially train GCNN with rotation and translation attacks (ablation)GCNN · ShapeNet partspatial non-smoothness: GCNN: 0.050{ $\pm$0.019} -> adv-GCNN: 0.054{ $\pm$0.110}; excluding knife: 0.049{ $\pm$0.020} -> 0.022{ $\pm$0.008}Mixed
use rotation-invariant architecture (ablation)PointNet++ and DGCNN · 3D point cloud classificationrotation sensitivity: PointNet++: 0.002{ $\pm$0.001}; DGCNN: 0.010{ $\pm$0.004}Improved
increase selected region size by partitioning into 16 rather than 32 regions (ablation)PointNet and DGCNN · ModelNet10rotation sensitivity: PointNet: 0.159{ $\pm$0.070} -> 0.292{ $\pm$0.117}; DGCNN: 0.174{ $\pm$0.075} -> 0.336{ $\pm$0.144}Hurt
use more training samples (ModelNet40 rather than ModelNet10) (ablation)PointNet and DGCNN · ModelNet40rotation sensitivity: PointNet: 0.159{ $\pm$0.070} -> 0.162{ $\pm$0.073}; DGCNN: 0.174{ $\pm$0.075} -> 0.158{ $\pm$0.065}No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy