About
Contact & Profiles
A5006669978
Research Areas
- Semantic Web and Ontologies
- Image and Video Quality Assessment
- Electromagnetic Simulation and Numerical Methods
- Radiative Heat Transfer Studies
- Numerical methods in inverse problems
- IoT and Edge/Fog Computing
- Computer Graphics and Visualization Techniques
- Numerical methods in engineering
- Electromagnetic Scattering and Analysis
- Context-Aware Activity Recognition Systems
Korea Advanced Institute of Science and Technology
2000-2025
10.1109/tmc.2025.3556998
article
EN
IEEE Transactions on Mobile Computing
2025-01-01
[S0022-1481(00)00304-2]
10.1115/1.1315597
article
EN
Journal of Heat Transfer
2000-06-21
When deployed in mobile scenarios, deep learning models often suffer from performance degradation due to domain shifts. Test-Time Adaptation (TTA) offers a viable solution, but current approaches face latency issues on resource-constrained devices. We propose TESLA: Time-Efficient Sparse and Lightweight strategy for real-time applications, which skips adaptation specific batches increase the inference sample rate. Our method balances model accuracy speed by accumulating domain-informative...
10.1145/3643832.3661442
article
EN
cc-by
2024-06-03
Coming Soon ...