Search Results for author:
Found 38 papers, 4 papers with code
EdgeOL: Efficient in-situ Online Learning on Edge Devices
Emerging applications, such as robot-assisted eldercare and object recognition, generally employ deep learning neural networks (DNNs) and naturally require: i) handling streaming-in inference requests and ii) adapting to possible deployment scenario changes.
A Dataset and Benchmark for Copyright Protection from Text-to-Image Diffusion Models
Copyright is a legal right that grants creators the exclusive authority to reproduce, distribute, and profit from their creative works.
Enabling On-Device Large Language Model Personalization with Self-Supervised Data Selection and Synthesis
While it is possible to obtain annotation locally by directly asking users to provide preferred responses, such annotations have to be sparse to not affect user experience.
Additional Positive Enables Better Representation Learning for Medical Images
This paper presents a new way to identify additional positive pairs for BYOL, a state-of-the-art (SOTA) self-supervised learning framework, to improve its representation learning ability.
BiTrackGAN: Cascaded CycleGANs to Constraint Face Aging
With the increased accuracy of modern computer vision technology, many access control systems are equipped with face recognition functions for faster identification.
Development of A Real-time POCUS Image Quality Assessment and Acquisition Guidance System
Point-of-care ultrasound (POCUS) is one of the most commonly applied tools for cardiac function imaging in the clinical routine of the emergency department and pediatric intensive care unit.
Self-supervised On-device Federated Learning from Unlabeled Streams
The ubiquity of edge devices has led to a growing amount of unlabeled data produced at the edge.
Enabling Weakly-Supervised Temporal Action Localization from On-Device Learning of the Video Stream
To enable W-TAL models to learn from a long, untrimmed streaming video, we propose an efficient video learning approach that can directly adapt to new environments.
Action Detection
Weakly-supervised Temporal Action Localization
+1
Federated Self-Supervised Contrastive Learning and Masked Autoencoder for Dermatological Disease Diagnosis
Self-supervised learning (SSL) methods, contrastive learning (CL) and masked autoencoders (MAE), can leverage the unlabeled data to pre-train models, followed by fine-tuning with limited labels.
Achieving Fairness in Dermatological Disease Diagnosis through Automatic Weight Adjusting Federated Learning and Personalization
The framework is divided into two stages: In the first in-FL stage, clients with different skin types are trained in a federated learning process to construct a global model for all skin types.
Distributed Contrastive Learning for Medical Image Segmentation
However, when adopting CL in FL, the limited data diversity on each site makes federated contrastive learning (FCL) ineffective.
Sustainable AI Processing at the Edge
In particular, we explore the use of processing-in-memory (PIM) approaches, mobile GPU accelerators, and recently released FPGAs, and compare them with novel Racetrack memory PIM.
H2H: Heterogeneous Model to Heterogeneous System Mapping with Computation and Communication Awareness
The heterogeneity in ML models comes from multi-sensor perceiving and multi-task learning, i. e., multi-modality multi-task (MMMT), resulting in diverse deep neural network (DNN) layers and computation patterns.
Federated Contrastive Learning for Volumetric Medical Image Segmentation
However, in medical imaging analysis, each site may only have a limited amount of data and labels, which makes learning ineffective.
FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis
By pruning the parameters based on this importance difference, we can reduce the accuracy difference between the privileged group and the unprivileged group to improve fairness without a large accuracy drop.
The Larger The Fairer? Small Neural Networks Can Achieve Fairness for Edge Devices
Results show that FaHaNa can identify a series of neural networks with higher fairness and accuracy on a dermatology dataset.
EF-Train: Enable Efficient On-device CNN Training on FPGA Through Data Reshaping for Online Adaptation or Personalization
In this work, we design EF-Train, an efficient DNN training accelerator with a unified channel-level parallelism-based convolution kernel that can achieve end-to-end training on resource-limited low-power edge-level FPGAs.
Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning
The recently developed self-supervised learning approach, contrastive learning (CL), can leverage the unlabeled data to pre-train a model, after which the model is fine-tuned on limited labeled data for dermatological disease diagnosis.
Synthetic Data Can Also Teach: Synthesizing Effective Data for Unsupervised Visual Representation Learning
To tackle this problem, we propose a data generation framework with two methods to improve CL training by joint sample generation and contrastive learning.
Decentralized Unsupervised Learning of Visual Representations
To tackle this problem, we propose a collaborative contrastive learning framework consisting of two approaches: feature fusion and neighborhood matching, by which a unified feature space among clients is learned for better data representations.
Data-Efficient Contrastive Learning by Differentiable Hard Sample and Hard Positive Pair Generation
In this way, the main model learns to cluster hard positives by pulling the representations of similar yet distinct samples together, by which the representations of similar samples are well-clustered and better representations can be learned.
Federated Contrastive Representation Learning with Feature Fusion and Neighborhood Matching
Federated learning (FL) enables distributed clients to learn a shared model for prediction while keeping the training data local on each client.
Hardware-aware Real-time Myocardial Segmentation Quality Control in Contrast Echocardiography
At the data acquisition time, the operator could not know the quality of the segmentation results.
Hardware Aware Neural Architecture Search
Neural Architecture Search
+1
Positional Contrastive Learning for Volumetric Medical Image Segmentation
The success of deep learning heavily depends on the availability of large labeled training sets.
Enabling On-Device Self-Supervised Contrastive Learning With Selective Data Contrast
After a model is deployed on edge devices, it is desirable for these devices to learn from unlabeled data to continuously improve accuracy.
Enabling Efficient On-Device Self-supervised Contrastive Learning by Data Selection
In this paper, we propose a framework to automatically select the most representative data from unlabeled input stream on-the-fly, which only requires the use of a small data buffer for dynamic learning.
FGNAS: FPGA-Aware Graph Neural Architecture Search
The success of gragh neural networks (GNNs) in the past years has aroused grow-ing interest and effort in designing best models to handle graph-structured data.
Personalized Deep Learning for Ventricular Arrhythmias Detection on Medical IoT Systems
We equip the system with real-time inference on both intracardiac and surface rhythm monitors.
Towards Cardiac Intervention Assistance: Hardware-aware Neural Architecture Exploration for Real-Time 3D Cardiac Cine MRI Segmentation
Experimental results on ACDC MICCAI 2017 dataset demonstrate that our hardware-aware multi-scale NAS framework can reduce the latency by up to 3. 5 times and satisfy the real-time constraints, while still achieving competitive segmentation accuracy, compared with the state-of-the-art NAS segmentation framework.
Standing on the Shoulders of Giants: Hardware and Neural Architecture Co-Search with Hot Start
To tackle this issue, HotNAS builds a chain of tools to design hardware to support compression, based on which a global optimizer is developed to automatically co-search all the involved search spaces.
Enabling On-Device CNN Training by Self-Supervised Instance Filtering and Error Map Pruning
For example, when training ResNet-110 on CIFAR-10, we achieve 68% computation saving while preserving full accuracy and 75% computation saving with a marginal accuracy loss of 1. 3%.
Intermittent Inference with Nonuniformly Compressed Multi-Exit Neural Network for Energy Harvesting Powered Devices
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.
Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators
In this paper, we are the first to bring the computing-in-memory architecture, which can easily transcend the memory wall, to interplay with the neural architecture search, aiming to find the most efficient neural architectures with high network accuracy and maximized hardware efficiency.
On Neural Architecture Search for Resource-Constrained Hardware Platforms
With 30, 000 LUTs, a light-weight design is found to achieve 82. 98\% accuracy and 1293 images/second throughput, compared to which, under the same constraints, the traditional method even fails to find a valid solution.
Hardware/Software Co-Exploration of Neural Architectures
We propose a novel hardware and software co-exploration framework for efficient neural architecture search (NAS).
Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Search
In addition, with a performance abstraction model to analyze the latency of neural architectures without training, our framework can quickly prune architectures that do not satisfy the specification, leading to higher efficiency.
DAC-SDC Low Power Object Detection Challenge for UAV Applications
The 55th Design Automation Conference (DAC) held its first System Design Contest (SDC) in 2018.
An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing
However, in these works, the memory design optimization is neglected for weight storage, which will inevitably result in large hardware cost.
