Related papers: Experimentally Realizing Convolution Processing in…
Continuous convolution has recently gained prominence due to its ability to handle irregularly sampled data and model long-term dependency. Also, the promising experimental results of using large convolutional kernels have catalyzed the…
In the recent years important experimental advances in resonant electro-optic modulators as high efficient sources for coherent frequency combs and as devices for quantum information transfer have been realized, where strong optical and…
Convolution is an efficient technique to obtain abstract feature representations using hierarchical layers in deep networks. Although performing convolution in Euclidean geometries is fairly straightforward, its extension to other…
Recent advancements in convolutional neural network (CNN)-based techniques for remote sensing pansharpening have markedly enhanced image quality. However, conventional convolutional modules in these methods have two critical drawbacks.…
Modern microelectronic processors have migrated towards parallel computing architectures with many-core processors. However, such expansion comes with diminishing returns exacted by the high cost of data movement between individual…
Recent learning-based lossless image compression methods encode an image in the unit of subimages and achieve comparable performances to conventional non-learning algorithms. However, these methods do not consider the performance drop in…
Inference of standard convolutional neural networks (CNNs) on FPGAs often incurs high latency and a long initiation interval due to the deep nested loops required to densely convolve every input pixel regardless of its feature value.…
Kernels are often developed and used as implicit mapping functions that show impressive predictive power due to their high-dimensional feature space representations. In this study, we gradually construct a series of simple feature maps that…
The fast Fourier transform, FFT, is a useful and prevalent algorithm in signal processing. It characterizes the spectral components of a signal, or is used in combination with other operations to perform more complex computations such as…
Quantum physics has brought enhanced capability in various sensing applications. Despite challenges from noise and loss in the radio-frequency (RF) domain, [Phys. Rev. Lett. 124, 150502 (2020)] demonstrates a route for enhanced RF-receiver…
Computational techniques have gained significant traction in photonics, enabling the co-design of hardware and data processing algorithms to drastically simplify optical system architectures and improve their performance. However, their…
Convolutional Neural Networks have revolutionized vision applications. There are image domains and representations, however, that cannot be handled by standard CNNs (e.g., spherical images, superpixels). Such data are usually processed…
Understanding the internal process of ConvNets is commonly done using visualization techniques. However, these techniques do not usually provide a tool for estimating the stability of a ConvNet against noise. In this paper, we show how to…
In StyleGAN, convolution kernels are shaped by both static parameters shared across images and dynamic modulation factors $w^+\in\mathcal{W}^+$ specific to each image. Therefore, $\mathcal{W}^+$ space is often used for image inversion and…
Convolution operator is the core of convolutional neural networks (CNNs) and occupies the most computation cost. To make CNNs more efficient, many methods have been proposed to either design lightweight networks or compress models. Although…
RF photonic transversal signal processors, which combine reconfigurable electrical digital signal processing and high-bandwidth photonic processing, provide a powerful solution for achieving adaptive high-speed information processing.…
The principle of translation equivariance (if an input image is translated an output image should be translated by the same amount), led to the development of convolutional neural networks that revolutionized machine vision. Other…
Photonic technologies have shown a promising way to build high-speed and high-energy-efficiency neural network accelerators. In previously presented photonic neural networks, architectures are mainly designed for fully-connected layers.…
The synthetic frequency dimension, which realizes fictitious spatial dimensions from the spectral degree of freedom, has emerged as a promising platform for engineering artificial gauge fields in studying quantum simulations and topological…
Multidimensional imaging, capturing image data in more than two dimensions, has been an emerging field with diverse applications. Due to the limitation of two-dimensional detectors in obtaining the high-dimensional image data, computational…