danfenghong / eccv2018_j-play Goto Github PK

Thanks for your sharing!
It's very helpful to my research. But on the hyperspectral image Indian_Pines, when I use a small number of samples for training (for example, 5 samples), the program will report an error. The reason is that the program lacks a function called 'mySVD'.
The function is openly available at http://www.cad.zju.edu.cn/home/dengcai/Data/DimensionReduction.html.
I would like to thank Prof. Deng Cai.

Thanks for your sharing! It's very helpful to my research. I have a question about the code. The JPSA is a two-stream multilayered regression model involving the two input sources: 1) pixelwise and 2) superpixelwise spectral signatures and the same output(ground truth). But l do not see the input of the supempixel segmentation part and the superpixel segmentation of images in the code. l dont know if l understand the meaning of the paper correctly?Looking forward to your reply, thank you！