Abstract: Convolution is fundamental in digital signal processing across many applications. Existing works enable N-point linear convolution via N-point right-angle circular convolution (RCC) based on ...
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 ...
In this paper, we tackle the high computational overhead of transformers for lightweight image super-resolution. (SR). Motivated by the observations of self-attention's inter-layer repetition, we ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results