Related papers: BlankSkip: Early-exit Object Detection onboard Nan…

Modern applications such as autonomous vehicles, intelligent surveillance, and smart city systems increasingly require object detection on resource-constrained edge devices. Yet, there is still limited understanding of how different object…

Although 3D Convolutional Neural Networks (CNNs) are essential for most learning based applications involving dense 3D data, their applicability is limited due to excessive memory and computational requirements. Compressing such networks by…

Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial intelligence (AI), including computer vision, natural language processing and speech recognition. However, their superior performance comes at the…

Spacecraft operations are highly critical, demanding impeccable reliability and safety. Ensuring the optimal performance of a spacecraft requires the early detection and mitigation of anomalies, which could otherwise result in unit or…

In the realm of aerial imaging, the ability to detect small objects is pivotal for a myriad of applications, encompassing environmental surveillance, urban design, and crisis management. Leveraging RetinaNet, this work unveils DDR-Net: a…

Object detection and classification is one of the most important computer vision problems. Ever since the introduction of deep learning \cite{krizhevsky2012imagenet}, we have witnessed a dramatic increase in the accuracy of this object…

Deep Neural Networks (DNNs) have shown significant advantages in a wide variety of domains. However, DNNs are becoming computationally intensive and energy hungry at an exponential pace, while at the same time, there is a vast demand for…

Well-trained deep neural networks (DNNs) treat all test samples equally during prediction. Adaptive DNN inference with early exiting leverages the observation that some test examples can be easier to predict than others. This paper presents…

Deep neural networks (DNNs) are reshaping the field of information processing. With their exponential growth challenging existing electronic hardware, optical neural networks (ONNs) are emerging to process DNN tasks in the optical domain…

Spiking neural networks (SNNs) offer inherent energy efficiency due to their event-driven computation model, making them promising for edge AI deployment. However, their practical adoption is limited by the computational overhead of deep…

Vision-Language Models (VLMs) are increasingly applied in autonomous driving for unified perception and reasoning, but high inference latency hinders real-time deployment. Early-exit reduces latency by terminating inference at intermediate…

On-device training is essential for user personalisation and privacy. With the pervasiveness of IoT devices and microcontroller units (MCUs), this task becomes more challenging due to the constrained memory and compute resources, and the…

Addressing airport traffic jams is one of the most crucial and challenging tasks in the remote sensing field, especially for the busiest airports. Several solutions have been employed to address this problem depending on the airplane…

Deep convolutional neural networks (CNNs) are the deep learning model of choice for performing object detection, classification, semantic segmentation and natural language processing tasks. CNNs require billions of operations to process a…

Object detection is a basic but challenging task in computer vision, which plays a key role in a variety of industrial applications. However, object detectors based on deep learning usually require greater storage requirements and longer…

Training a neural network (NN) typically relies on some type of curve-following method, such as gradient descent (GD) (and stochastic gradient descent (SGD)), ADADELTA, ADAM or limited memory algorithms. Convergence for these algorithms…

The need to execute Deep Neural Networks (DNNs) at low latency and low power at the edge has spurred the development of new heterogeneous Systems-on-Chips (SoCs) encapsulating a diverse set of hardware accelerators. How to optimally map a…

Deep Neural Networks (DNNs) have drawn attention because of their outstanding performance on various tasks. However, deploying full-fledged DNNs in resource-constrained devices (edge, mobile, IoT) is difficult due to their large size. To…

Spiking neural networks (SNNs) are brain-inspired energy-efficient models that encode information in spatiotemporal dynamics. Recently, deep SNNs trained directly have shown great success in achieving high performance on classification…

The increasing penetration rate of new energy in the power system has put forward higher requirements for the operation and maintenance of substations and transmission lines. Using the Unmanned Aerial Vehicles (UAV) to identify foreign…