HIGHLIGHTS
- who: Wijayanti Nurul Khotimah and colleagues from the Department of Computer Science and Software Engineering, The University of Western Australia have published the research: SC-CAN: Spectral Convolution and Channel Attention Network for Wheat Stress Classification, in the Journal: (JOURNAL) of 22/08/2022
- what: Because not all feature maps produced by the dilated convolutional layers are important the authors propose a channel attention module that weights the feature maps according to their importance level. To overcome the aforementioned shortcomings, the authors propose spectral convolution modules that consist of dilated convolutional layers with 1D filters . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.