Prototype distribution correction for few-shot point cloud classification
Image Processing|更新时间:2024-09-10
|
Prototype distribution correction for few-shot point cloud classification
“In the field of small sample point cloud classification, researchers have proposed a prototype correction method based on Gaussian distribution, which effectively alleviates the overfitting problem and enhances the robustness of the model.”
Chinese Journal of Liquid Crystals and DisplaysVol. 39, Issue 9, Pages: 1243-1254(2024)
作者机构:
1.中国科学院 福建物质结构研究所, 福建 福州 350002
2.中国科学院大学, 北京 100049
3.上海宇航系统工程研究所, 上海 201108
4.中国福建光电信息科学技术创新实验室, 福建 福州 350108
作者简介:
基金信息:
Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China(2021ZZ120);Quanzhou Science and Technology Plan(2021C065L)
FENG Yuanzhi, XIA Yu, GUO Jielong, et al. Prototype distribution correction for few-shot point cloud classification[J]. Chinese journal of liquid crystals and displays, 2024, 39(9): 1243-1254.
DOI:
FENG Yuanzhi, XIA Yu, GUO Jielong, et al. Prototype distribution correction for few-shot point cloud classification[J]. Chinese journal of liquid crystals and displays, 2024, 39(9): 1243-1254. DOI: 10.37188/CJLCD.2023-0374.
Prototype distribution correction for few-shot point cloud classification