Related papers: A Disentangled Representation Learning Framework f…
Since rain streaks show a variety of shapes and directions, learning the degradation representation is extremely challenging for single image deraining. Existing methods are mainly targeted at designing complicated modules to implicitly…
Planning coverage path for multiple robots in a decentralized way enhances robustness to coverage tasks handling uncertain malfunctions. To achieve high efficiency in a distributed manner for each single robot, a comprehensive understanding…
Disentangled representation learning aims to uncover latent variables underlying the observed data, and generally speaking, rather strong assumptions are needed to ensure identifiability. Some approaches rely on sufficient changes on the…
Beamforming design for intelligent reflecting surface (IRS)-assisted multi-user communication (IRS-MUC) systems critically depends on the acquisition of accurate channel state information (CSI). However, channel estimation (CE) in IRS-MUC…
Large-scale multimodal contrastive learning has recently achieved impressive success in learning rich and transferable representations, yet it remains fundamentally limited by the uniform treatment of feature dimensions and the neglect of…
Capturing interpretable variations has long been one of the goals in disentanglement learning. However, unlike the independence assumption, interpretability has rarely been exploited to encourage disentanglement in the unsupervised setting.…
Enhancing the quality of low-light images plays a very important role in many image processing and multimedia applications. In recent years, a variety of deep learning techniques have been developed to address this challenging task. A…
In this paper, we propose a learned scalable/progressive image compression scheme based on deep neural networks (DNN), named Bidirectional Context Disentanglement Network (BCD-Net). For learning hierarchical representations, we first adopt…
This paper investigates the integrated sensing and communication (ISAC) in vehicle-to-infrastructure (V2I) networks. To realize ISAC, an effective beamforming design is essential which however, highly depends on the availability of accurate…
Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision. A good general representation can be fine-tuned for new target tasks using…
Semantic communication, augmented by knowledge bases (KBs), offers substantial reductions in transmission overhead and resilience to errors. However, existing methods predominantly rely on end-to-end training to construct KBs, often failing…
Modeling group actions on latent representations enables controllable transformations of high-dimensional image data. Prior works applying group-theoretic priors or modeling transformations typically operate in the high-dimensional data…
Parametric system identification methods estimate the parameters of explicitly defined physical systems from data. Yet, they remain constrained by the need to provide an explicit function space, typically through a predefined library of…
Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric properties of these…
The problem of high-dimensional and large-scale representation of visual data is addressed from an unsupervised learning perspective. The emphasis is put on discrete representations, where the description length can be measured in bits and…
The process of decomposing target images into their internal properties is a difficult task due to the inherent ill-posed nature of the problem. The lack of data required to train a network is a one of the reasons why the decomposing…
Deploying deep learning neural networks on edge devices, to accomplish task specific objectives in the real-world, requires a reduction in their memory footprint, power consumption, and latency. This can be realized via efficient model…
Time series forecasting has witnessed significant progress with deep learning. While prevailing approaches enhance forecasting performance by modifying architectures or introducing novel enhancement strategies, they often fail to…
Symmetry-based disentangled representation learning leverages the group structure of environment transformations to uncover the latent factors of variation. Prior approaches to symmetry-based disentanglement have required strong prior…
Standard Adjacency Spectral Embedding (ASE) relies on a global low-rank assumption often incompatible with the sparse, transitive structure of real-world networks, causing local geometric features to be 'smeared'. To address this, we…