Search Results for author:
Found 21 papers, 3 papers with code
Consistency-Guided Temperature Scaling Using Style and Content Information for Out-of-Domain Calibration
In this paper, we propose consistency-guided temperature scaling (CTS), a new temperature scaling strategy that can significantly enhance the OOD calibration performance by providing mutual supervision among data samples in the source domains.
EvoFed: Leveraging Evolutionary Strategies for Communication-Efficient Federated Learning
This global fitness vector is then disseminated back to the nodes, each of which applies the same update to be synchronized to the global model.
Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization
In domain generalization (DG), the target domain is unknown when the model is being trained, and the trained model should successfully work on an arbitrary (and possibly unseen) target domain during inference.
SplitGP: Achieving Both Generalization and Personalization in Federated Learning
A fundamental challenge to providing edge-AI services is the need for a machine learning (ML) model that achieves personalization (i. e., to individual clients) and generalization (i. e., to unseen data) properties concurrently.
Locally Supervised Learning with Periodic Global Guidance
Locally supervised learning aims to train a neural network based on a local estimation of the global loss function at each decoupled module of the network.
Task-Adaptive Feature Transformer with Semantic Enrichment for Few-Shot Segmentation
The task-conditioned feature transformation allows an effective utilization of the semantic information in novel classes to generate tight segmentation masks.
GenLabel: Mixup Relabeling using Generative Models
Mixup is a data augmentation method that generates new data points by mixing a pair of input data.
Sageflow: Robust Federated Learning against Both Stragglers and Adversaries
While federated learning (FL) allows efficient model training with local data at edge devices, among major issues still to be resolved are: slow devices known as stragglers and malicious attacks launched by adversaries.
Accelerating Federated Split Learning via Local-Loss-Based Training
Federated learning (FL) operates based on model exchanges between the server and the clients, and suffers from significant communication as well as client-side computation burden.
Few-Round Learning for Federated Learning
Of central issues that may limit a widespread adoption of FL is the significant communication resources required in the exchange of updated model parameters between the server and individual clients over many communication rounds.
FedMes: Speeding Up Federated Learning with Multiple Edge Servers
Our key idea is to utilize the devices located in the overlapping areas between the coverage of edge servers; in the model-downloading stage, the devices in the overlapping areas receive multiple models from different edge servers, take the average of the received models, and then update the model with their local data.
Sself: Robust Federated Learning against Stragglers and Adversaries
While federated learning allows efficient model training with local data at edge devices, two major issues that need to be resolved are: slow devices known as stragglers and malicious attacks launched by adversaries.
Communication-Computation Efficient Secure Aggregation for Federated Learning
Through extensive real-world experiments, we demonstrate that our scheme, using only $20 \sim 30\%$ of the resources required in the conventional scheme, maintains virtually the same levels of reliability and data privacy in practical federated learning systems.
Task-Adaptive Feature Transformer for Few-Shot Segmentation
Few-shot learning allows machines to classify novel classes using only a few labeled samples.
XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning
The base and novel classifiers quickly adapt to a given task by utilizing the TAR.
CAFENet: Class-Agnostic Few-Shot Edge Detection Network
Since there is no existing dataset for few-shot semantic edge detection, we construct two new datasets, FSE-1000 and SBD-$5^i$, and evaluate the performance of the proposed CAFENet on them.
Task-Adaptive Clustering for Semi-Supervised Few-Shot Classification
Our method employs explicit task-conditioning in which unlabeled sample clustering for the current task takes place in a new projection space different from the embedding feature space.
Election Coding for Distributed Learning: Protecting SignSGD against Byzantine Attacks
Recent advances in large-scale distributed learning algorithms have enabled communication-efficient training via SignSGD.
Semi-Supervised Few-Shot Learning with a Controlled Degree of Task-Adaptive Conditioning
Our method employs explicit task-conditioning in which unlabeled sample clustering for the current task takes place in a new projection space different from the embedding feature space.
TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning
The training loss is obtained based on a distance metric between the query and the reference vectors in the projection space.
Meta-Learner with Linear Nulling
We propose a meta-learning algorithm utilizing a linear transformer that carries out null-space projection of neural network outputs.
