With deep learning becoming a more prominent approach for automatic classification of three-dimensional point cloud data, a key bottleneck is the amount of high quality training data, especially when

DataCite Commons2020-08-26 更新90

Mean accuracy results of image segmentation by type of datasets (horizontal axis: Type of test datasets, vertical axis: Type of training datasets).

水体图像分割

合成数据训练

(A) Reservoir low sensitivity_Real, (B) Reservoir high sensitivity_Real, (C) Pool low sensitivity_Real, (D) Pool high sensitivity_Real, (E) Reservoir low sensitivity_Synth, (F) Reservoir high sensitiv

NIAID Data Ecosystem50

Comparison of using different data compositions of synthetic images for training the classifier and then testing it on the 724 real images.

合成数据训练

图像分类泛化

Comparison of using different data compositions of synthetic images for training the classifier and then testing it on the 724 real images.

NIAID Data Ecosystem20