Test-time augmentation for 3D point cloud classification and segmentation
Data augmentation is a powerful technique to enhance the performance of a deep learning task but has received less attention in 3D deep learning. It is well known that when 3D shapes are sparsely represented with low point density, the performance of the downstream tasks drops significantly. This wo...
Saved in:
Main Authors: | VU, Tuan-Anh, SARKAR, Srinjay, ZHANG, Zhiyuan, HUA, Binh-Son, YEUNG, Sai-Kit |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8963 https://ink.library.smu.edu.sg/context/sis_research/article/9966/viewcontent/2311.13152v1.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Global context aware convolutions for 3D point cloud understanding
by: ZHANG, Zhiyuan, et al.
Published: (2020) -
ShellNet: Efficient point cloud convolutional neural networks using concentric shells statistics
by: ZHANG, Zhiyuan, et al.
Published: (2019) -
Rotation invariant convolutions for 3D point clouds deep learning
by: ZHANG, Zhiyuan, et al.
Published: (2019) -
RIConv++: Effective rotation invariant convolutions for 3D point clouds deep learning
by: ZHANG, Zhiyuan, et al.
Published: (2022) -
Self-supervised multi-class pre-training for unsupervised anomaly detection and segmentation in medical images
by: TIAN, Yu, et al.
Published: (2021)