Related papers: SAIL: Unsupervised Spatial-Angular Interpretable F…
Aims. We present an innovative artificial neural network (ANN) architecture, called Generative ANN (GANN), that computes the forward model, that is it learns the function that relates the unknown outputs (stellar atmospheric parameters, in…
This paper presents a methodology and workflow that overcome the limitations of the conventional Generative Adversarial Networks (GANs) for geological facies modeling. It attempts to improve the training stability and guarantee the…
Acquisition of Synthetic Aperture Sonar (SAS) datasets is bottlenecked by the costly deployment of SAS imaging systems, and even when data acquisition is possible,the data is often skewed towards containing barren seafloor rather than…
Sensing is an integral part of 6G and beyond systems, providing exceptional environmental perception along with communication. Radio frequency (RF)-based sensing often relies on simplified geometric assumptions (e.g., point scatterers or…
With the rise of large radio interferometric telescopes, particularly the SKA, there is a growing demand for computationally efficient image reconstruction techniques. Existing reconstruction methods, such as the CLEAN algorithm or proximal…
Imitation Learning (IL) enables agents to mimic expert behavior by learning from demonstrations. However, traditional IL methods require large amounts of medium-to-high-quality demonstrations as well as actions of expert demonstrations,…
Recent years have seen substantial progress in neural generation of text, images, and audio, supported by mature training pipelines and large-scale optimization. For graphs, however, comparable progress has been more limited. We attribute…
Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems since they can generate more visually realistic images and video frames. However, these models often introduce side effects into the outputs,…
Image generation and image completion are rapidly evolving fields, thanks to machine learning algorithms that are able to realistically replace missing pixels. However, generating large high resolution images, with a large level of details,…
Arterial spin labeling (ASL) magnetic resonance imaging (MRI) is a powerful imaging technology that can measure cerebral blood flow (CBF) quantitatively. However, since only a small portion of blood is labeled compared to the whole tissue…
Imitation learning methods have demonstrated considerable success in teaching autonomous systems complex tasks through expert demonstrations. However, a limitation of these methods is their lack of interpretability, particularly in…
Hierarchical Imitation Learning (HIL) is a promising approach for tackling long-horizon decision-making tasks. While it is a challenging task due to the lack of detailed supervisory labels for sub-goal learning, and reliance on hundreds to…
Traditional implicit generative models are capable of learning highly complex data distributions. However, their training involves distinguishing real data from synthetically generated data using adversarial discriminators, which can lead…
Increasing concerns on intelligent spectrum sensing call for efficient training and inference technologies. In this paper, we propose a novel federated learning (FL) framework, dubbed federated spectrum learning (FSL), which exploits the…
Image super-resolution (SR) is an underdetermined inverse problem, where a large number of plausible high-resolution images can explain the same downsampled image. Most current single image SR methods use empirical risk minimisation, often…
Compared to traditional imitation learning methods such as DAgger and DART, intervention-based imitation offers a more convenient and sample efficient data collection process to users. In this paper, we introduce Reinforced…
Biologically inspired algorithms for simultaneous localization and mapping (SLAM) such as RatSLAM have been shown to yield effective and robust robot navigation in both indoor and outdoor environments. One drawback however is the…
Learning super-resolution (SR) network without the paired low resolution (LR) and high resolution (HR) image is difficult because direct supervision through the corresponding HR counterpart is unavailable. Recently, many real-world SR…
Harvesting data from distributed Internet of Things (IoT) devices with multiple autonomous unmanned aerial vehicles (UAVs) is a challenging problem requiring flexible path planning methods. We propose a multi-agent reinforcement learning…
Recently, generative AI technologies have emerged as a significant advancement in artificial intelligence field, renowned for their language and image generation capabilities. Meantime, space-air-ground integrated network (SAGIN) is an…