Related papers: MatchNAS: Optimizing Edge AI in Sparse-Label Data …
Real-time video analytics on edge devices for changing scenes remains a difficult task. As edge devices are usually resource-constrained, edge deep neural networks (DNNs) have fewer weights and shallower architectures than general DNNs. As…
Deep Neural Networks (DNNs) have become key components of many safety-critical applications such as autonomous driving and medical diagnosis. However, DNNs have been shown suffering from poor robustness because of their susceptibility to…
The empowering unmanned aerial vehicles (UAVs) have been extensively used in providing intelligence such as target tracking. In our field experiments, a pre-trained convolutional neural network (CNN) is deployed at the UAV to identify a…
Designing deep networks that meet strict latency and accuracy constraints on edge accelerators increasingly relies on hardware-aware optimization, including neural architecture search (NAS) guided by device-level metrics. Yet most…
Deep Learning approaches based on Convolutional Neural Networks (CNNs) are extensively utilized and very successful in a wide range of application areas, including image classification and speech recognition. For the execution of trained…
Along with the fast evolution of deep neural networks, the hardware system is also developing rapidly. As a promising solution achieving high scalability and low manufacturing cost, multi-accelerator systems widely exist in data centers,…
Data-driven fault detection has been regarded as a 3D image segmentation task. The models trained from synthetic data are difficult to generalize in some surveys. Recently, training 3D fault segmentation using sparse manual 2D slices is…
The deployment of deep neural networks (DNNs) on resource-constrained edge devices such as field-programmable gate arrays (FPGAs) requires a careful balance of latency, power, and resource usage while maintaining high accuracy. Existing…
Mobile devices run deep learning models for various purposes, such as image classification and speech recognition. Due to the resource constraints of mobile devices, researchers have focused on either making a lightweight deep neural…
Neural Architecture Search (NAS) has enabled automatic discovery of more efficient neural network architectures, especially for mobile and embedded vision applications. Although recent research has proposed ways of quickly estimating…
Recent advances in Deep Neural Networks (DNNs) have demonstrated outstanding performance across various domains. However, their large size is a challenge for deployment on resource-constrained devices such as mobile, edge, and IoT…
Deep learning datasets are expanding at an unprecedented pace, creating new challenges for data processing in model training pipelines. A crucial aspect of these pipelines is dataset shuffling, which significantly improves unbiased learning…
Although deep neural networks are typically computationally expensive to use, technological advances in both the design of hardware platforms and of neural network architectures, have made it possible to use powerful models on edge devices.…
Deep Neural Networks (DNNs) are rapidly being adopted by the automotive industry, due to their impressive performance in tasks that are essential for autonomous driving. Object segmentation is one such task: its aim is to precisely locate…
Neural Architecture Search (NAS) is increasingly popular to automatically explore the accuracy versus computational complexity trade-off of Deep Learning (DL) architectures. When targeting tiny edge devices, the main challenge for DL…
The unprecedented performance of deep neural networks (DNNs) has led to large strides in various Artificial Intelligence (AI) inference tasks, such as object and speech recognition. Nevertheless, deploying such AI models across commodity…
Smart IoT-based systems often desire continuous execution of multiple latency-sensitive Deep Learning (DL) applications. The edge servers serve as the cornerstone of such IoT-based systems, however, their resource limitations hamper the…
Modern machine learning workloads use large models, with complex structures, that are very expensive to execute. The devices that execute complex models are becoming increasingly heterogeneous as we see a flourishing of domain-specific…
With the increasing data volume, there is a trend of using large-scale pre-trained models to store the knowledge into an enormous number of model parameters. The training of these models is composed of lots of dense algebras, requiring a…
In computer vision, the performance of deep neural networks (DNNs) is highly related to the feature extraction ability, i.e., the ability to recognize and focus on key pixel regions in an image. However, in this paper, we quantitatively and…