Picture for Seunghan Yang

Seunghan Yang

Feature Diversification and Adaptation for Federated Domain Generalization

Add code
Jul 11, 2024
Viaarxiv icon

Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference

Add code
Jun 11, 2024
Viaarxiv icon

Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data

Add code
Aug 31, 2023
Viaarxiv icon

Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts

Add code
Aug 17, 2023
Viaarxiv icon

Progressive Random Convolutions for Single Domain Generalization

Add code
Apr 02, 2023
Viaarxiv icon

Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes

Add code
Jul 24, 2022
Figure 1 for Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes
Figure 2 for Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes
Figure 3 for Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes
Figure 4 for Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes
Viaarxiv icon

QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design

Add code
Jun 28, 2022
Figure 1 for QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design
Figure 2 for QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design
Figure 3 for QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design
Figure 4 for QTI Submission to DCASE 2021: residual normalization for device-imbalanced acoustic scene classification with efficient design
Viaarxiv icon

Personalized Keyword Spotting through Multi-task Learning

Add code
Jun 28, 2022
Figure 1 for Personalized Keyword Spotting through Multi-task Learning
Figure 2 for Personalized Keyword Spotting through Multi-task Learning
Figure 3 for Personalized Keyword Spotting through Multi-task Learning
Figure 4 for Personalized Keyword Spotting through Multi-task Learning
Viaarxiv icon

Domain Agnostic Few-shot Learning for Speaker Verification

Add code
Jun 28, 2022
Figure 1 for Domain Agnostic Few-shot Learning for Speaker Verification
Figure 2 for Domain Agnostic Few-shot Learning for Speaker Verification
Figure 3 for Domain Agnostic Few-shot Learning for Speaker Verification
Figure 4 for Domain Agnostic Few-shot Learning for Speaker Verification
Viaarxiv icon

Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting

Add code
Jun 28, 2022
Figure 1 for Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting
Figure 2 for Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting
Figure 3 for Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting
Figure 4 for Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting
Viaarxiv icon