Related papers: Tensorized Optical Multimodal Fusion Network
Tensor decomposition has been widely used in machine learning and high-volume data analysis. However, large-scale tensor factorization often consumes huge memory and computing cost. Meanwhile, modernized computing hardware such as tensor…
In facing with the explosive Internet traffic growth, optical transport networks based on WDM technologies forming the core part of Internet infrastructure carrying multi-Tb/s has to be re-considered from both designing, planning, operation…
In this research paper, the problems dealing with sensor network architecture, sensor fusion are addressed. Time/Computationally optimal network architectures are investigated. Some novel ideas on sensor fusion are proposed.
Opto-electronic computing combines the complementary strengths of photonics and electronics to deliver ultrahigh computational throughput with high energy efficiency. However, its practical deployment for real-world applications has been…
This work presents a novel method for task optimization in industrial plants using quantum-inspired tensor network technology. This method obtains the best possible combination of tasks on a set of machines with directed constraints while…
Multimodal learning mimics the reasoning process of the human multi-sensory system, which is used to perceive the surrounding world. While making a prediction, the human brain tends to relate crucial cues from multiple sources of…
With its unique parallel processing capability, optical neural network has shown low-power consumption in image recognition and speech processing. At present, the manufacturing technology of programmable photonic chip is not mature, and the…
RGB and thermal image fusion have great potential to exhibit improved semantic segmentation in low-illumination conditions. Existing methods typically employ a two-branch encoder framework for multimodal feature extraction and design…
Tensor processing is the cornerstone of modern technological advancements, powering critical applications in data analytics and artificial intelligence. While optical computing offers exceptional advantages in bandwidth, parallelism, and…
The main idea of multimodal recommendation is the rational utilization of the item's multimodal information to improve the recommendation performance. Previous works directly integrate item multimodal features with item ID embeddings,…
Vision Transformers have achieved state-of-the-art performance in a wide range of computer vision tasks, but their practical deployment is limited by high computational and memory costs. In this paper, we introduce a novel tensor-based…
Sparse attention is a core building block in many leading neural network models, from graph-structured learning to sparse sequence modeling. It can be decomposed into a sequence of three sparse matrix operations (3S): sampled dense-dense…
Tensor networks are factorisations of high rank tensors into networks of lower rank tensors and have primarily been used to analyse quantum many-body problems. Tensor networks have seen a recent surge of interest in relation to supervised…
This paper investigates an uplink non-orthogonal multiple access (NOMA)-based mobile-edge computing (MEC) network. Our objective is to minimize the total energy consumption of all users including transmission energy and local computation…
Feature fusion, the combination of features from different layers or branches, is an omnipresent part of modern network architectures. It is often implemented via simple operations, such as summation or concatenation, but this might not be…
This work presents a multi-layered methodology for efficiently accelerating multimodal foundation models (MFMs). It combines hardware and software co-design of transformer blocks with an optimization pipeline that reduces computational and…
Current multi-modality driving frameworks normally fuse representation by utilizing attention between single-modality branches. However, the existing networks still suppress the driving performance as the Image and LiDAR branches are…
The optical neural network (ONN) is a promising hardware platform for next-generation neuromorphic computing due to its high parallelism, low latency, and low energy consumption. However, previous integrated photonic tensor cores (PTCs)…
Machine learning-based applications are increasingly prevalent in IoT devices. The power and storage constraints of these devices make it particularly challenging to run modern neural networks, limiting the number of new applications that…
Medical images play an important role in clinical applications. Multimodal medical images could provide rich information about patients for physicians to diagnose. The image fusion technique is able to synthesize complementary information…