Related papers: Learning to Gridize: Segment Physical World by Wir…
The convergence of GD and SGD when training mildly parameterized neural networks starting from random initialization is studied. For a broad range of models and loss functions, including the most commonly used square loss and cross entropy…
While 3D Gaussian Splatting enables high-quality real-time rendering, existing Gaussian-based frameworks for 3D semantic segmentation still face significant challenges in boundary recognition accuracy. To address this, we propose a novel…
Network alignment is useful for multiple applications that require increasingly large graphs to be processed. Existing research approaches this as an optimization problem or computes the similarity based on node representations. However,…
A novel technique is proposed which enables each transmitter to acquire global channel state information (CSI) from the sole knowledge of individual received signal power measurements, which makes dedicated feedback or inter-transmitter…
Model compression techniques are recently gaining explosive attention for obtaining efficient AI models for various real-time applications. Channel pruning is one important compression strategy and is widely used in slimming various DNNs.…
Brain-Computer Interfaces (BCIs) based on Motor Execution (ME) and Motor Imagery (MI) electroencephalogram (EEG) signals offer a direct pathway for human-machine interaction. However, developing robust decoding models remains challenging…
The motor imagery (MI) classification has been a prominent research topic in brain-computer interfaces based on electroencephalography (EEG). Over the past few decades, the performance of MI-EEG classifiers has seen gradual enhancement. In…
Network alignment is the task of establishing one-to-one correspondences between the nodes of different graphs. Although finding a plethora of applications in high-impact domains, this task is known to be NP-hard in its general form.…
This paper introduces a novel framework designed to achieve a high compression ratio in Split Learning (SL) scenarios where resource-constrained devices are involved in large-scale model training. Our investigations demonstrate that…
Image harmonization aims to modify the color of the composited region with respect to the specific background. Previous works model this task as a pixel-wise image-to-image translation using UNet family structures. However, the model size…
Multi-echo Chemical Shift Encoded methods for Fat-Water quantification are growing in clinical use due to their ability to estimate and correct some confounding effects. State of the art CSE water-fat separation approaches rely on a…
The development of algorithms for enhancing the resilience and efficiency of the power grid requires performance evaluation with real topologies of power transmission networks. However, due to security reasons, such topologies and…
In this paper, we aim to efficiently and accurately predict the static channel impulse response (CIR) with only the user's position information and a set of channel instances obtained within a certain wireless communication environment.…
Split learning (SL) transfers most of the training workload to the server, which alleviates computational burden on client devices. However, the transmission of intermediate feature representations, referred to as smashed data, incurs…
Traditional localization algorithms based on features such as time difference of arrival are impaired by non-line of sight propagation, which negatively affects the consistency that they expect among distance estimates. Instead,…
In this paper, a novel framework is proposed for channel charting (CC)-aided localization in millimeter wave networks. In particular, a convolutional autoencoder model is proposed to estimate the three-dimensional location of wireless user…
Large-scale distributed training requires significant communication bandwidth for gradient exchange that limits the scalability of multi-node training, and requires expensive high-bandwidth network infrastructure. The situation gets even…
Brain signals are important quantitative data for understanding physiological activities and diseases of human brain. Most existing studies pay attention to supervised learning methods, which, however, require high-cost clinical labels. In…
Edge computing allows artificial intelligence and machine learning models to be deployed on edge devices, where they can learn from local data and collaborate to form a global model. Federated learning (FL) is a distributed machine learning…
Channel state information (CSI) is essential for adaptive beamforming and maintaining robust links in wireless communication systems. However, acquiring CSI incurs significant overhead, consuming up to 25% of spectrum resources in 5G…