The 3D crop data obtained during cultivation is of great signifcance to screening excellent varieties in modern breeding and improvement on crop yield. With the rapid development of deep learning, ...

One of the central aspects of U-Nets are up- and downsampling operations: In the encoder portion, the features are iteratively downsampled, before they are recombined with their later upsampled ...

Abstract: In this paper we present methods for downsampling datasets defined on graphs (i.e., graph-signals) by extending downsampling results for traditional N-dimensional signals. In particular, we ...

Abstract: The state-of-the-art downsampling method for graph signals has been constructed by using maximum spanning trees (MSTs) of the graphs. For the graph signals defined on unweighted densely ...