Related papers: FUSION: A Flexible Unified Simulator for Intellige…
Modern ML methods excel when training data is IID, large-scale, and well labeled. Learning in less ideal conditions remains an open challenge. The sub-fields of few-shot, continual, transfer, and representation learning have made…
This article proposes a universal simulation platform for simulating systems undergoing duress. In other words, this paper introduces a total simulation package which includes a number of methods of simulating the flexibility of a given…
Sixth-Generation (6G) networks are set to provide reliable, widespread, and ultra-low-latency mobile broadband communications for a variety of industries. In this regard, the Internet of Drones (IoD) represents a key component for the…
This letter presents a multi-scenario adaptable intelligent robot simulation platform based on LIDAR-inertial fusion, with three main features: (1 The platform includes an versatile robot model that can be freely controlled through manual…
Recent advances in diffusion bridge models leverage Doob's $h$-transform to establish fixed endpoints between distributions, demonstrating promising results in image translation and restoration tasks. However, these approaches often produce…
All-optical diffractive neural networks (DNNs) offer a promising alternative to electronics-based neural network processing due to their low latency, high throughput, and inherent spatial parallelism. However, the lack of reconfigurability…
Deep learning has been used to demonstrate end-to-end neural network learning for autonomous vehicle control from raw sensory input. While LiDAR sensors provide reliably accurate information, existing end-to-end driving solutions are mainly…
The increasing demand for high-speed optical interconnects necessitates integrated photonic and electronic solutions. Electro-optic co-simulation is key to meeting these requirements, which works by importing interoperable photonic models…
With the rising imaging resolution of handheld devices, existing multi-exposure image fusion algorithms struggle to generate a high dynamic range image with ultra-high resolution in real-time. Apart from that, there is a trend to design a…
The exponential expansion of IoT and 5G-Advanced applications has enlarged the attack surface for DDoS, malware, and zero-day intrusions. We propose an intrusion detection system that fuses a convolutional neural network (CNN), a…
Data fusion is an essential task in various domains, enabling the integration of multi-source information to enhance data quality and insights. One key application is in satellite remote sensing, where fusing multi-sensor observations can…
Mobile and embedded platforms are increasingly required to efficiently execute computationally demanding DNNs across heterogeneous processing elements. At runtime, the available hardware resources to DNNs can vary considerably due to other…
Image fusion aims to integrate complementary information from multiple source images to produce a more informative and visually consistent representation, benefiting both human perception and downstream vision tasks. Despite recent…
Diffractive optical neural networks (DONNs), leveraging free-space light wave propagation for ultra-parallel, high-efficiency computing, have emerged as promising artificial intelligence (AI) accelerators. However, their inherent lack of…
Collaborative visual perception methods have gained widespread attention in the autonomous driving community in recent years due to their ability to address sensor limitation problems. However, the absence of explicit depth information…
Recent years have seen a growing research interest in applications of Deep Neural Networks (DNN) on autonomous vehicle technology. The trend started with perception and prediction a few years ago and it is gradually being applied to motion…
Flexible optical networks (FONs) are being adopted to accommodate the increasingly heterogeneous traffic in today's Internet. However, in presence of high traffic load, not all offered traffic can be satisfied at all time. As carried…
Reconfigurable intelligent surface (RIS) is an excellent use case for line-of-sight (LOS) based technologies such as free-space optical (FSO) communications. In this paper, we analyze the performance of RIS-empowered FSO (RISE-FSO) systems…
Infrared and visible image fusion aim to integrate modality strengths for visually enhanced, informative images. Visible imaging in real-world scenarios is susceptible to dynamic environmental brightness fluctuations, leading to texture…
Novel-view synthesis through diffusion models has demonstrated remarkable potential for generating diverse and high-quality images. Yet, the independent process of image generation in these prevailing methods leads to challenges in…