相关论文: MobileTL: On-device Transfer Learning with Inverte…

Human Activity Recognition (HAR) is an attractive topic to perceive human behavior and supplying assistive services. Besides the classical inertial unit and vision-based HAR methods, new sensing technologies, such as ultrasound and…

As the demand for mobile robots continues to increase, social navigation has emerged as a critical task, driving active research into deep reinforcement learning (RL) approaches. However, because pedestrian dynamics and social conventions…

Image deblurring is a critical stage in mobile image signal processing pipelines, where the ability to restore fine structures and textures must be balanced with real-time constraints on edge devices. While recent deep networks such as…

Memory-efficient transfer learning (METL) approaches have recently achieved promising performance in adapting pre-trained models to downstream tasks. They avoid applying gradient backpropagation in large backbones, thus significantly…

A new algorithm for incremental learning in the context of Tiny Machine learning (TinyML) is presented, which is optimized for low-performance and energy efficient embedded devices. TinyML is an emerging field that deploys machine learning…

The increasing computational demands of deep learning models pose significant challenges for edge devices. To address this, we propose a memristor-based circuit design for MobileNetV3, specifically for image classification tasks. Our design…

Multimodal transformers integrate diverse data types like images, audio, and text, advancing tasks such as audio-visual understanding and image-text retrieval; yet their high parameterization limits deployment on resource-constrained edge…

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

We present four different robust transfer learning and data augmentation strategies for robust mobile scene recognition. By training three mobile-ready (EfficientNetB0, MobileNetV2, MobileNetV3) and two large-scale baseline (VGG16,…

The Internet of Things (IoT) has been increasingly used in our everyday lives as well as in numerous industrial applications. However, due to limitations in computing and power capabilities, IoT devices need to send their respective tasks…

The display devices like HDR10 televisions are increasingly prevalent in our daily life for visualizing high dynamic range (HDR) images. But the majority of media images on the internet remain in 8-bit standard dynamic range (SDR) format.…

Parameter-efficient transfer learning (PETL) has emerged as a flourishing research field for adapting large pre-trained models to downstream tasks, greatly reducing trainable parameters while grappling with memory challenges during…

In this paper, we propose an edge-assisted split federated learning framework to facilitate large language model (LLM) fine-tuning on heterogeneous mobile devices while alleviating memory pressures on both mobile devices and the edge…

Objective: Model based deep learning (MBDL) has been challenging to apply to the reconstruction of 3D non-Cartesian MRI acquisitions due to extreme GPU memory demand (>250 GB using traditional backpropagation) primarily because the entire…

Machine learning models deployed on edge devices have enabled numerous exciting new applications, such as humanoid robots, AR glasses, and autonomous vehicles. However, the computing resources available on these edge devices are not…

Traffic prediction represents one of the crucial tasks for smartly optimizing the mobile network. Recently, Artificial Intelligence (AI) has attracted attention to solve this problem thanks to its ability in cognizing the state of the…

Memory-efficient backpropagation (MeBP) has enabled first-order fine-tuning of large language models (LLMs) on mobile devices with less than 1GB memory. However, MeBP requires backward computation through all transformer layers at every…

On-device tuning of deep neural networks enables long-term adaptation at the edge while preserving data privacy. However, the high computational and memory demands of backpropagation pose significant challenges for ultra-low-power,…

On-device control agents, especially on mobile devices, are responsible for operating mobile devices to fulfill users' requests, enabling seamless and intuitive interactions. Integrating Multimodal Large Language Models (MLLMs) into these…

Estimating individualized treatment rules (ITRs) is fundamental to precision medicine, where the goal is to tailor treatment decisions to individual patient characteristics. While numerous methods have been developed for ITR estimation,…