相关论文: Adversarial Score-Based Generative Models for MMSE…

Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This…

Recent studies have shown that deep learning models are vulnerable to specifically crafted adversarial inputs that are quasi-imperceptible to humans. In this letter, we propose a novel method to detect adversarial inputs, by augmenting the…

We present variational generative adversarial networks, a general learning framework that combines a variational auto-encoder with a generative adversarial network, for synthesizing images in fine-grained categories, such as faces of a…

In practical affine frequency division multiplexing (AFDM) systems, the intricate coupling of oscillator phase noise (PN) and off-grid fractional shifts traps conventional estimators in a severe high-SNR error floor. To address these…

Although the recent progress is substantial, deep learning methods can be vulnerable to the maliciously generated adversarial examples. In this paper, we present a novel training procedure and a thresholding test strategy, towards robust…

Sequential recommendation as an emerging topic has attracted increasing attention due to its important practical significance. Models based on deep learning and attention mechanism have achieved good performance in sequential…

We present a neural network based predictor which is derived by starting from the linear minimum mean squared error (LMMSE) predictor and by further making two key assumptions. With these assumptions, we first derive a weighted sum of LMMSE…

In the years since Goodfellow et al. introduced Generative Adversarial Networks (GANs), there has been an explosion in the breadth and quality of generative model applications. Despite this work, GANs still have a long way to go before they…

Generative adversarial networks (GANs) provide an algorithmic framework for constructing generative models with several appealing properties: they do not require a likelihood function to be specified, only a generating procedure; they…

Convolutional neural networks (CNNs) have been demonstrated their powerful ability to extract discriminative features for hyperspectral image classification. However, general deep learning methods for CNNs ignore the influence of complex…

This article introduces a new Neural Network stochastic model to generate a 1-dimensional stochastic field with turbulent velocity statistics. Both the model architecture and training procedure ground on the Kolmogorov and Obukhov…

In recent years, applying deep learning (DL) to assess structural damages has gained growing popularity in vision-based structural health monitoring (SHM). However, both data deficiency and class-imbalance hinder the wide adoption of DL in…

Dense depth estimation and 3D reconstruction of a surgical scene are crucial steps in computer assisted surgery. Recent work has shown that depth estimation from a stereo images pair could be solved with convolutional neural networks.…

End-to-end deep learning for communication systems, i.e., systems whose encoder and decoder are learned, has attracted significant interest recently, due to its performance which comes close to well-developed classical encoder-decoder…

Massive random access is an important technology for achieving ultra-massive connectivity in next-generation wireless communication systems. It aims to address key challenges during the initial access phase, including active user detection…

Recent deep learning based approaches have shown remarkable success on object segmentation tasks. However, there is still room for further improvement. Inspired by generative adversarial networks, we present a generic end-to-end adversarial…

Allowing effective inference of latent vectors while training GANs can greatly increase their applicability in various downstream tasks. Recent approaches, such as ALI and BiGAN frameworks, develop methods of inference of latent variables…

Despite the wide use of machine learning in adversarial settings including computer security, recent studies have demonstrated vulnerabilities to evasion attacks---carefully crafted adversarial samples that closely resemble legitimate…

Adversarial attacks exploit the vulnerabilities of convolutional neural networks by introducing imperceptible perturbations that lead to misclassifications, exposing weaknesses in feature representations and decision boundaries. This paper…

This paper is concerned with channel estimation in MIMO systems with few-bit ADCs. In these systems, a linear minimum mean-squared error (MMSE) channel estimator obtained in closed-form is not an optimal solution. We first consider a deep…