Search Results for author:
Found 42 papers, 12 papers with code
Distributed Traffic Synthesis and Classification in Edge Networks: A Federated Self-supervised Learning Approach
FS-GAN is composed of multiple distributed Generative Adversarial Networks (GANs), with a set of generators, each being designed to generate synthesized data samples following the distribution of an individual service traffic, and each discriminator being trained to differentiate the synthesized data samples and the real data samples of a local dataset.
Adversarial Learning for Implicit Semantic-Aware Communications
In this paper, we consider the implicit semantic communication problem in which hidden relations and closely related semantic terms that cannot be recognized from the source signals need to also be delivered to the destination user.
Time-sensitive Learning for Heterogeneous Federated Edge Intelligence
A joint optimization algorithm is proposed to minimize the overall time consumption of model training by selecting participating edge servers, local epoch number.
Residual Degradation Learning Unfolding Framework with Mixing Priors across Spectral and Spatial for Compressive Spectral Imaging
However, in the data subproblem, the used sensing matrix is ill-suited for the real degradation process due to the device errors caused by phase aberration, distortion; in the prior subproblem, it is important to design a suitable model to jointly exploit both spatial and spectral priors.
Imitation Learning-based Implicit Semantic-aware Communication Networks: Multi-layer Representation and Collaborative Reasoning
A federated GCN-based collaborative reasoning solution is proposed to allow multiple edge servers to jointly construct a shared semantic interpretation model based on decentralized knowledge datasets.
GMSS: Graph-Based Multi-Task Self-Supervised Learning for EEG Emotion Recognition
GMSS has the ability to learn more general representations by integrating multiple self-supervised tasks, including spatial and frequency jigsaw puzzle tasks, and contrastive learning tasks.
ModulE: Module Embedding for Knowledge Graphs
Specifically, under our framework, we introduce a more generic embedding method, ModulE, which projects entities to a module.
Robust Depth Completion with Uncertainty-Driven Loss Functions
In this work, we introduce uncertainty-driven loss functions to improve the robustness of depth completion and handle the uncertainty in depth completion.
Progressive Graph Convolution Network for EEG Emotion Recognition
Moreover, motivated by the observation of the relationship between coarse- and fine-grained emotions, we adopt a dual-head module that enables the PGCN to progressively learn more discriminative EEG features, from coarse-grained (easy) to fine-grained categories (difficult), referring to the hierarchical characteristic of emotion.
Uncertainty-Driven Loss for Single Image Super-Resolution
Specifically, we introduce variance estimation characterizing the uncertainty on a pixel-by-pixel basis into SISR solutions so the targeted pixels in a high-resolution image (mean) and their corresponding uncertainty (variance) can be learned simultaneously.
Federated Traffic Synthesizing and Classification Using Generative Adversarial Networks
With the fast growing demand on new services and applications as well as the increasing awareness of data protection, traditional centralized traffic classification approaches are facing unprecedented challenges.
PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network
With a PG-CTC decoder, we gather high-level character classification vectors from two-dimensional space and decode them into text symbols without NMS and RoI operations involved, which guarantees high efficiency.
Ranked #1 on
Scene Text Detection
on ICDAR 2015
(Accuracy metric)
Searching Efficient Model-guided Deep Network for Image Denoising
Similar to the success of NAS in high-level vision tasks, it is possible to find a memory and computationally efficient solution via NAS with highly competent denoising performance.
Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging
Different from existing GSM models using hand-crafted scale priors (e. g., the Jeffrey's prior), we propose to learn the scale prior through a deep convolutional neural network (DCNN).
A new communication paradigm: from bit accuracy to semantic fidelity
In this article, we deploy semantics to solve the spectrum and power bottleneck and propose a first understanding and then transmission framework with high semantic fidelity.
Networking and Internet Architecture
Optical Flow Estimation via Motion Feature Recovery
In this paper, we discover that the lost information is related to a large quantity of motion features (more than 40%) computed from the popular discriminative cost-volume feature would completely vanish due to invalid sampling, leading to the low efficiency of optical flow learning.
Unsupervised Curriculum Domain Adaptation for No-Reference Video Quality Assessment
From this adaptation, we split the data in target domain into confident and uncertain subdomains using the proposed uncertainty-based ranking function, through measuring their prediction confidences.
Temporal Graph Modeling for Skeleton-based Action Recognition
Specifically, the constructed temporal relation graph explicitly builds connections between semantically related temporal features to model temporal relations between both adjacent and non-adjacent time steps.
Optimizing Resource-Efficiency for Federated Edge Intelligence in IoT Networks
The data uploading performance of IoT network and the computational capacity of edge servers are entangled with each other in influencing the FL model training process.
EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation
This paper addresses the challenging unsupervised scene flow estimation problem by jointly learning four low-level vision sub-tasks: optical flow $\textbf{F}$, stereo-depth $\textbf{D}$, camera pose $\textbf{P}$ and motion segmentation $\textbf{S}$.
2D+3D Facial Expression Recognition via Discriminative Dynamic Range Enhancement and Multi-Scale Learning
In 2D+3D facial expression recognition (FER), existing methods generate multi-view geometry maps to enhance the depth feature representation.
Towards Self-learning Edge Intelligence in 6G
Edge intelligence, also called edge-native artificial intelligence (AI), is an emerging technological framework focusing on seamless integration of AI, communication networks, and mobile edge computing.
A Novel Transferability Attention Neural Network Model for EEG Emotion Recognition
So it is necessary to give more attention to the EEG samples with strong transferability rather than forcefully training a classification model by all the samples.
Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network
Deep neural networks (DNNs) based methods have achieved great success in single image super-resolution (SISR).
Towards Ubiquitous AI in 6G with Federated Learning
One of the key challenges is the difficulty to implement distributed AI across a massive number of heterogeneous devices.
MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment
The underlying idea is to learn the meta-knowledge shared by human when evaluating the quality of images with various distortions, which can then be adapted to unknown distortions easily.
A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
Detecting scene text of arbitrary shapes has been a challenging task over the past years.
Ranked #18 on
Scene Text Detection
on ICDAR 2015
Knowledge-guided Semantic Computing Network
Besides, to enhance the recognition ability of the semantic tree in aspects of the diversity, randomicity and variability, we use the traditional neural network to aid the semantic tree to learn some indescribable features.
Learning Hybrid Sparsity Prior for Image Restoration: Where Deep Learning Meets Sparse Coding
State-of-the-art approaches toward image restoration can be classified into model-based and learning-based.
Joint Demosaicing and Denoising with Perceptual Optimization on a Generative Adversarial Network
Image demosaicing - one of the most important early stages in digital camera pipelines - addressed the problem of reconstructing a full-resolution image from so-called color-filter-arrays.
Perceptual Compressive Sensing
In detail, we employ perceptual loss, defined on feature level, to enhance the structure information of the recovered images.
Full Image Recover for Block-Based Compressive Sensing
In measurement part, the input image is adaptively measured block by block to acquire a group of measurements.
ConvCSNet: A Convolutional Compressive Sensing Framework Based on Deep Learning
Instead of reconstructing individual blocks, the whole image is reconstructed from the linear convolutional measurements.
Denoising Prior Driven Deep Neural Network for Image Restoration
Then, the iterative process is unfolded into a deep neural network, which is composed of multiple denoisers modules interleaved with back-projection (BP) modules that ensure the observation consistencies.
Fully Convolutional Measurement Network for Compressive Sensing Image Reconstruction
Recently, deep learning methods have made a significant improvement in compressive sensing image reconstruction task.
Real-Time Illegal Parking Detection System Based on Deep Learning
Experiments show that the system can achieve a 99% accuracy and real-time (25FPS) detection with strong robustness in complex environments.
Adaptive Measurement Network for CS Image Reconstruction
In this paper, we propose an adaptive measurement network in which measurement is obtained by learning.
Feature-Fused SSD: Fast Detection for Small Objects
We propose a multi-level feature fusion method for introducing contextual information in SSD, in order to improve the accuracy for small objects.
Learning Parametric Sparse Models for Image Super-Resolution
More specifically, the parametric sparse prior of the desirable high-resolution (HR) image patches are learned from both the input low-resolution (LR) image and a training image dataset.
Low-Rank Tensor Approximation With Laplacian Scale Mixture Modeling for Multiframe Image Denoising
Patch-based low-rank models have shown effective in exploiting spatial redundancy of natural images especially for the application of image denoising.
Learning Parametric Distributions for Image Super-Resolution: Where Patch Matching Meets Sparse Coding
Existing approaches toward Image super-resolution (SR) is often either data-driven (e. g., based on internet-scale matching and web image retrieval) or model-based (e. g., formulated as an Maximizing a Posterior estimation problem).
High-Speed Hyperspectral Video Acquisition With a Dual-Camera Architecture
We propose a novel dual-camera design to acquire 4D high-speed hyperspectral (HSHS) videos with high spatial and spectral resolution.
