Search Results for author:
Found 16 papers, 11 papers with code
Astraea: Self-balancing Federated Learning for Improving Classification Accuracy of Mobile Deep Learning Applications
However, unlike the common training dataset, the data distribution of the edge computing system is imbalanced which will introduce biases in the model training and cause a decrease in accuracy of federated learning applications.
FedGroup: Efficient Clustered Federated Learning via Decomposed Data-Driven Measure
In this paper, we propose a novel clustered federated learning (CFL) framework FedGroup, in which we 1) group the training of clients based on the similarities between the clients' optimization directions for high training performance; 2) construct a new data-driven distance measure to improve the efficiency of the client clustering procedure.
Flexible Clustered Federated Learning for Client-Level Data Distribution Shift
Federated Learning (FL) enables the multiple participating devices to collaboratively contribute to a global neural network model while keeping the training data locally.
Improve robustness of DNN for ECG signal classification:a noise-to-signal ratio perspective
However, despite of the excellent performance in classification accuracy, it has been shown that DNNs are highly vulnerable to adversarial attacks: subtle changes in input of a DNN can lead to a wrong classification output with high confidence.
A Regularization Method to Improve Adversarial Robustness of Neural Networks for ECG Signal Classification
Electrocardiogram (ECG) is the most widely used diagnostic tool to monitor the condition of the human heart.
Enhance CNN Robustness Against Noises for Classification of 12-Lead ECG with Variable Length
Thus, it is challenging and essential to improve robustness of DNNs against adversarial noises for ECG signal classification, a life-critical application.
Increasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural Networks
However, adversarial training samples with excessive noises can harm standard accuracy, which may be unacceptable for many medical image analysis applications.
SymTC: A Symbiotic Transformer-CNN Net for Instance Segmentation of Lumbar Spine MRI
In this work, we proposed SymTC, an innovative lumbar spine MR image segmentation model that combines the strengths of Transformer and Convolutional Neural Network (CNN).
Adversarial Robustness Study of Convolutional Neural Network for Lumbar Disk Shape Reconstruction from MR images
We utilized the PGD-based algorithm for IND adversarial attacks and extended it for OOD adversarial attacks to generate OOD adversarial samples for model testing.
Attention-based Shape-Deformation Networks for Artifact-Free Geometry Reconstruction of Lumbar Spine from MR Images
The deformed template reveals the lumbar spine geometry in an image.
Supervised neural machine translation based on data augmentation and improved training \& inference process
This is the second time for SRCB to participate in WAT.
An Algorithm for Out-Of-Distribution Attack to Neural Network Encoder
Deep neural networks (DNNs), especially convolutional neural networks, have achieved superior performance on image classification tasks.
CQ-VAE: Coordinate Quantized VAE for Uncertainty Estimation with Application to Disk Shape Analysis from Lumbar Spine MRI Images
In this paper, we propose a powerful generative model to learn a representation of ambiguity and to generate probabilistic outputs.
Optimal Distribution Design for Irregular Repetition Slotted ALOHA with Multi-Packet Reception
Associated with multi-packet reception at the access point, irregular repetition slotted ALOHA (IRSA) holds a great potential in improving the access capacity of massive machine type communication systems.
Adaptive Adversarial Training to Improve Adversarial Robustness of DNNs for Medical Image Segmentation and Detection
It is known that Deep Neural networks (DNNs) are vulnerable to adversarial attacks, and the adversarial robustness of DNNs could be improved by adding adversarial noises to training data (e. g., the standard adversarial training (SAT)).
Optimizing Illuminant Estimation in Dual-Exposure HDR Imaging
Within camera ISP pipeline, illuminant estimation is a crucial step aiming to estimate the color of the global illuminant in the scene.
