Abstract: We propose reparameterized refocusing convolution (RefConv) as a replacement for regular convolutional layers, which is a plug-and-play module to improve the performance without any ...
Abstract: In recent years, convolutional neural networks (CNNs)-based methods achieve cracking performance on hyperspectral image (HSI) classification tasks, due to its hierarchical structure and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results