Related papers: DRIFT-Net: A Spectral--Coupled Neural Operator for…
Spectral graph contrastive learning often constructs low- and high-frequency views to capture complementary graph signals, but these views are commonly combined by graph-level or node-agnostic fusion rules. We show that graph-level fusion…
Reinforcement learning agents based on Transformer architectures have achieved impressive performance on sequential decision-making tasks, but their reliance on dense matrix operations makes them ill-suited for energy-constrained,…
By learning the mappings between infinite function spaces using carefully designed neural networks, the operator learning methodology has exhibited significantly more efficiency than traditional methods in solving complex problems such as…
Convolutional Neural Networks have become a cornerstone of medical image analysis due to their proficiency in learning hierarchical spatial features. However, this focus on a single domain is inefficient at capturing global, holistic…
Spiking Neural Networks (SNNs) operate with asynchronous discrete events (or spikes) which can potentially lead to higher energy-efficiency in neuromorphic hardware implementations. Many works have shown that an SNN for inference can be…
Deploying depth estimation networks in the real world requires high-level robustness against various adverse conditions to ensure safe and reliable autonomy. For this purpose, many autonomous vehicles employ multi-modal sensor systems,…
In many real-time applications, the deployment of deep neural networks is constrained by high computational cost and efficient lightweight neural networks are widely concerned. In this paper, we propose that depthwise convolution (DWC) is…
Vision transformers have been applied successfully for image recognition tasks. There have been either multi-headed self-attention based (ViT \cite{dosovitskiy2020image}, DeIT, \cite{touvron2021training}) similar to the original work in…
Deep learning is a promising, ultra-fast approach for inverse design in nano-optics, but despite fast advancement of the field, the computational cost of dataset generation, as well as of the training procedure itself remains a major…
Deep convolutional neural networks (DCNNs) based remote sensing (RS) image semantic segmentation technology has achieved great success used in many real-world applications such as geographic element analysis. However, strong dependency on…
Recent Graph Neural Networks (GNNs) combine spectral-spatial architectures for enhanced representation learning. However, limited attention has been paid to certified robustness, particularly regarding training strategies and underlying…
When solving partial differential equations (PDEs), classical numerical methods often require fine mesh grids and small time stepping to meet stability, consistency, and convergence conditions, leading to high computational cost. Recently,…
In this work, we propose to leverage a deep-learning (DL) based reconstruction framework for high quality Swept-Source Optical Coherence Tomography (SS-OCT) images, by incorporating wavelength ({\lambda}) space interferometric fringes.…
Beam selection for millimeter-wave links in a vehicular scenario is a challenging problem, as an exhaustive search among all candidate beam pairs cannot be assuredly completed within short contact times. We solve this problem via a novel…
Neural operators learn to map initial conditions to the terminal solution of partial differential equations (PDEs), providing a surrogate for the full operator mapping. This enables rapid prediction across different input configurations.…
Many current neural networks for medical imaging generalise poorly to data unseen during training. Such behaviour can be caused by networks overfitting easy-to-learn, or statistically dominant, features while disregarding other potentially…
Edge-cloud co-inference enables efficient deep neural network (DNN) deployment by splitting the architecture between an edge device and cloud server, crucial for resource-constraint edge devices. This approach requires balancing on-device…
Accurately predicting spatio-temporal network traffic is essential for dynamically managing computing resources in modern communication systems and minimizing energy consumption. Although spatio-temporal traffic prediction has received…
This paper introduces Dynamic Embeddings with Task-Oriented prompting (DETOT), a novel approach aimed at improving the adaptability and efficiency of machine learning models by implementing a flexible embedding layer. Unlike traditional…
This article introduces GIT-Net, a deep neural network architecture for approximating Partial Differential Equation (PDE) operators, inspired by integral transform operators. GIT-NET harnesses the fact that differential operators commonly…