This repository contains the official code for FlashFFTConv, a fast algorithm for computing long depthwise convolutions using the FFT algorithm. FlashFFTConv computes convolutions up to 7.93 times ...

Abstract: Dilated convolution is a powerful technique for expanding the receptive field without increasing the convolution kernel size, making it highly valuable in image segmentation tasks. However, ...

A windowed sinc function can implement a low-pass filter, and a two-dimensional convolutional filter can blur or sharpen images. In part 3 of this series, we introduced a low-pass filter based on the ...

Event-based cameras are bio-inspired vision sensors that mimic the sparse and asynchronous activation of the animal retina, offering advantages such as low latency and low computational load in ...

Non-invasive brain-computer interfaces (BCI) hold great promise in the field of neurorehabilitation. They are easy to use and do not require surgery, particularly in the area of motor imagery ...

Robustness is crucial for deploying deep learning models in real-world applications. Vision Transformers (ViTs) have shown strong robustness and state-of-the-art performance in various vision tasks ...

Abstract: In this paper, we propose Dynamic Residual Convolution (DRConv), an efficient method for computing input-specific local features while addressing the limitations of dynamic convolution.

For a non-regular "image", the same output size is given regardless of the kernel size. A typical image is shaped (N, 3, H, W), but my input is multivariate timeseries signal shaped (N, 1, ...