Related papers: Separating the EoR Signal with a Convolutional Den…
Denoising autoencoders (DAEs) have proven useful for unsupervised representation learning, but a thorough theoretical understanding is still lacking of how the input noise influences learning. Here we develop theory for how noise influences…
Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders. In this paper, we systematically investigate several design choices and find three insights which simplify and improve RAE. First, we study a…
Diffractive deep neural network (D2NN), known for its high speed and strong parallelism, has been widely applied across various fields, including pattern recognition, image processing, and image transmission. However, existing network…
Latent diffusion models have established a new state-of-the-art in high-resolution visual generation. Integrating Vision Foundation Model priors improves generative efficiency, yet existing latent designs remain largely heuristic. These…
Automatic image segmentation technology is critical to the visual analysis. The autoencoder architecture has satisfying performance in various image segmentation tasks. However, autoencoders based on convolutional neural networks (CNN) seem…
An end-to-end communications system based on Orthogonal Frequency Division Multiplexing (OFDM) is modeled as an autoencoder (AE) for which the transmitter (coding and modulation) and receiver (demodulation and decoding) are represented as…
Deep neural networks have achieved remarkable progress in enhancing low-light images by improving their brightness and eliminating noise. However, most existing methods construct end-to-end mapping networks heuristically, neglecting the…
Suitable lateral connections between encoder and decoder are shown to allow higher layers of a denoising autoencoder (dAE) to focus on invariant representations. In regular autoencoders, detailed information needs to be carried through the…
It is a challenging problem to detect and recognize targets on complex large-scene Synthetic Aperture Radar (SAR) images. Recently developed deep learning algorithms can automatically learn the intrinsic features of SAR images, but still…
The 21 cm intensity mapping provides a promising probe of the large-scale structure. Astrophysical foregrounds, as the main source of contamination to the cosmological 21 cm signal, persist in a wedge-like region of Fourier space due to the…
Self-supervised learning has been a powerful training paradigm to facilitate representation learning. In this study, we design a masked autoencoder (MAE) to guide deep learning models to learn electroencephalography (EEG) signal…
After deep generative models were successfully applied to image generation tasks, learning disentangled latent variables of data has become a crucial part of deep generative model research. Many models have been proposed to learn an…
Foreground removal is one of the biggest challenges in the detection of the Cosmic Dawn (CD) and Epoch of Reionization (EoR). Various foreground subtraction techniques have been developed based on the spectral smoothness of foregrounds.…
In industry, machine anomalous sound detection (ASD) is in great demand. However, collecting enough abnormal samples is difficult due to the high cost, which boosts the rapid development of unsupervised ASD algorithms. Autoencoder (AE)…
The key challenge in the observation of the redshifted 21-cm signal from cosmic reionization is its separation from the much brighter foreground emission. Such separation relies on the different spectral properties of the two components,…
Upcoming measurements of the high-redshift 21 cm signal from the Epoch of Reionization (EoR) are a promising probe of the astrophysics of the first galaxies and of cosmological parameters. In particular, the optical depth $\tau$ to the last…
Extracellular recordings are severely contaminated by a considerable amount of noise sources, rendering the denoising process an extremely challenging task that should be tackled for efficient spike sorting. To this end, we propose an…
Cryogenic electron tomography is a technique for imaging biological samples in 3D. A microscope collects a series of 2D projections of the sample, and the goal is to reconstruct the 3D density of the sample called the tomogram.…
Deep learning-based informative band selection methods on hyperspectral images (HSI) recently have gained intense attention to eliminate spectral correlation and redundancies. However, the existing deep learning-based methods either need…
Two-dimensional (2D) fast spin echo (FSE) techniques play a central role in the clinical magnetic resonance imaging (MRI) of knee joints. Moreover, three-dimensional (3D) FSE provides high-isotropic-resolution magnetic resonance (MR) images…