Related papers: NaNet: a Low-Latency, Real-Time, Multi-Standard Ne…

Recent advanced studies have spent considerable human efforts on optimizing network architectures for stereo matching but hardly achieved both high accuracy and fast inference speed. To ease the workload in network design, neural…

Graph Neural Networks (GNNs) are a promising deep learning approach for circumventing many real-world problems on graph-structured data. However, these models usually have at least one of four fundamental limitations: over-smoothing,…

Subgraph matching is a core operation in graph analytics, supporting a broad spectrum of applications from social network analysis to bioinformatics. Recent GPU-based approaches accelerate subgraph matching by leveraging parallelism but…

Neural Architecture Search (NAS) is quickly becoming the go-to approach to optimize the structure of Deep Learning (DL) models for complex tasks such as Image Classification or Object Detection. However, many other relevant applications of…

As recurrent neural networks become larger and deeper, training times for single networks are rising into weeks or even months. As such there is a significant incentive to improve the performance and scalability of these networks. While…

As AI workloads drive increasing memory requirements, domain-specific accelerators need higher-density on-chip memory beyond what current SRAM scaling trends can provide. Simultaneously, the vast amounts of short-lived data in these…

Recently, many convolutional neural network (CNN) methods have been designed for hyperspectral image (HSI) classification since CNNs are able to produce good representations of data, which greatly benefits from a huge number of parameters.…

Deep Neural Networks (DNNs) have been established as the state-of-the-art algorithm for advanced machine learning applications. Recently, CapsuleNets have improved the generalization ability, as compared to DNNs, due to their…

In recent years, the attention mechanism has demonstrated superior performance in various tasks, leading to the emergence of GAT and Graph Transformer models that utilize this mechanism to extract relational information from…

Graph neural networks (GNNs) start to gain momentum after showing significant performance improvement in a variety of domains including molecular science, recommendation, and transportation. Turning such performance improvement of GNNs into…

Typically, Ultra-deep neural network(UDNN) tends to yield high-quality model, but its training process is usually resource intensive and time-consuming. Modern GPU's scarce DRAM capacity is the primary bottleneck that hinders the…

With the continuous development of neural networks for computer vision tasks, more and more network architectures have achieved outstanding success. As one of the most advanced neural network architectures, DenseNet shortcuts all feature…

In this study, we introduce EdgeSegNet, a compact deep convolutional neural network for the task of semantic segmentation. A human-machine collaborative design strategy is leveraged to create EdgeSegNet, where principled network design…

Edge vision systems combining sensing and embedded processing promise low-latency, decentralized, and energy-efficient solutions that forgo reliance on the cloud. As opposed to conventional frame-based vision sensors, event-based cameras…

Non-orthogonal multiple access (NOMA) is an interesting technology that enables massive connectivity as required in future 5G and 6G networks. While purely linear processing already achieves good performance in NOMA systems, in certain…

Graph neural networks (GNN) analysis engines are vital for real-world problems that use large graph models. Challenges for a GNN hardware platform include the ability to (a) host a variety of GNNs, (b) handle high sparsity in input vertex…

The increased memory and processing capabilities of today's edge devices create opportunities for greater edge intelligence. In the domain of vision, the ability to adapt a Convolutional Neural Network's (CNN) structure and parameters to…

This work is for designing one-stage lightweight detectors which perform well in terms of mAP and latency. With baseline models each of which targets on GPU and CPU respectively, various operations are applied instead of the main operations…

A common theme of data acquisition systems is the transport of data from digitising front-end modules to stable storage and online analysis. A good choice today is to base this on the ubiquitous, commercially and cheaply available Ethernet…

Personalized recommendation is a ubiquitous application on the internet, with many industries and hyperscalers extensively leveraging Deep Learning Recommendation Models (DLRMs) for their personalization needs (like ad serving or movie…