.png){kind=icon}
.png){kind=icon}
Return
Selective structural ablation for efficient 3D point cloud signal processing
.png){kind=icon}
OA
AI
DOI：10.1016/j.sigpro.2026.110851.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• APES-Soft: a lightweight model for 3D point cloud classification. • Systematic ablation reduces the APES network complexity. • Achieves 93.8% accuracy, within the range of reported ModelNet40 results. • Balances high classification accuracy with low computational cost, including reduced parameter count, forward complexity, and inference latency. • Statistical tests support a cautious performance-retention claim rather than formal equivalence.
Keywords:
Ablation analysis
Computational efficiency
Convolutional neural networks
Point clouds
3D object classification
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.6
Papers:
9.9K
Citations:
1.7W