Related papers: Lightweight Remote Sensing Scene Classification on…
Deploying large and complex deep neural networks on resource-constrained edge devices poses significant challenges due to their computational demands and the complexities of non-convex optimization. Traditional compression methods such as…
Autonomous systems and smart-industry deployments increasingly split computation across near-sensor, edge, and cloud resources, where tight energy, latency, and reliability budgets demand run-time adaptivity. In practice, deciding what to…
I explored adapting Stable Diffusion v1.5 for generating domain-specific satellite and aerial images in remote sensing. Recognizing the limitations of existing models like Midjourney and Stable Diffusion, trained primarily on natural RGB…
Fully convolutional neural networks (FCNs) have shown their advantages in the salient object detection task. However, most existing FCNs-based methods still suffer from coarse object boundaries. In this paper, to solve this problem, we…
The growing demand for intelligent applications beyond the network edge, coupled with the need for sustainable operation, are driving the seamless integration of deep learning (DL) algorithms into energy-limited, and even energy-harvesting…
We propose AffordanceNet, a new deep learning approach to simultaneously detect multiple objects and their affordances from RGB images. Our AffordanceNet has two branches: an object detection branch to localize and classify the object, and…
Integrated sensing and communication (ISAC) and intelligent reflecting surface (IRS) are viewed as promising technologies for future generations of wireless networks. This paper investigates the channel estimation problem in an IRS-assisted…
This work aims to enable persistent, event-driven sensing and decision capabilities for energy-harvesting (EH)-powered devices by deploying lightweight DNNs onto EH-powered devices. However, harvested energy is usually weak and…
Dataset condensation, a concept within data-centric learning, efficiently transfers critical attributes from an original dataset to a synthetic version, maintaining both diversity and realism. This approach significantly improves model…
In this paper, we propose an efficient and fast object detector which can process hundreds of frames per second. To achieve this goal we investigate three main aspects of the object detection framework: network architecture, loss function…
Recent deep learning based salient object detection methods which utilize both saliency and boundary features have achieved remarkable performance. However, most of them ignore the complementarity between saliency features and boundary…
Salient object detection (SOD) in remote sensing images faces significant challenges due to large variations in object sizes, the computational cost of self-attention mechanisms, and the limitations of CNN-based extractors in capturing…
Ensemble models comprising of deep Convolutional Neural Networks (CNN) have shown significant improvements in model generalization but at the cost of large computation and memory requirements. In this paper, we present a framework for…
Effectively structuring deep knowledge plays a pivotal role in transfer from teacher to student, especially in semantic vision tasks. In this paper, we present a simple knowledge structure to exploit and encode information inside the…
Deep neural networks (DNNs) have succeeded in many different perception tasks, e.g., computer vision, natural language processing, reinforcement learning, etc. The high-performed DNNs heavily rely on intensive resource consumption. For…
Transformers are successfully applied to computer vision due to their powerful modeling capacity with self-attention. However, the excellent performance of transformers heavily depends on enormous training images. Thus, a data-efficient…
Diffusion Models have shown remarkable proficiency in image and video synthesis. As model size and latency increase limit user experience, hybrid edge-cloud collaborative framework was recently proposed to realize fast inference and…
Neural architecture search (NAS) has shown great promise in automatically designing lightweight models. However, conventional approaches are insufficient in training the supernet and pay little attention to actual robot hardware resources.…
The inference of Neural Networks is usually restricted by the resources (e.g., computing power, memory, bandwidth) on edge devices. In addition to improving the hardware design and deploying efficient models, it is possible to aggregate the…
Recent studies in Learning to Rank have shown the possibility to effectively distill a neural network from an ensemble of regression trees. This result leads neural networks to become a natural competitor of tree-based ensembles on the…