Search Results for author:
Found 2 papers, 2 papers with code
AKConv: Convolutional Kernel with Arbitrary Sampled Shapes and Arbitrary Number of Parameters
In response to the above questions, the Alterable Kernel Convolution (AKConv) is explored in this work, which gives the convolution kernel an arbitrary number of parameters and arbitrary sampled shapes to provide richer options for the trade-off between network overhead and performance.
RFAConv: Innovating Spatial Attention and Standard Convolutional Operation
In this paper, we propose a new perspective on the effectiveness of spatial attention, which is that the spatial attention mechanism essentially solves the problem of convolutional kernel parameter sharing.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
