A5032016982- Domain Adaptation and Few-Shot Learning
- Adversarial Robustness in Machine Learning
- Advanced Neural Network Applications
- COVID-19 diagnosis using AI
- Time Series Analysis and Forecasting
- Network Security and Intrusion Detection
- Anomaly Detection Techniques and Applications
Hyundai Motor Group (South Korea)
2021
Seoul National University
2021
As industries become automated and connectivity technologies advance, a wide range of systems continues to generate massive amounts data. Many approaches have been proposed extract principal indicators from the vast sea data represent entire system state. Detecting anomalies using these on time prevent potential accidents economic losses. Anomaly detection in multivariate series poses particular challenge because it requires simultaneous consideration temporal dependencies relationships...
Deep neural networks perform well in artificially- balanced datasets, but real-world data often has a long-tailed distribution. Recent studies have focused on developing unbiased classifiers to improve tail class performance. Despite the efforts learn fine classifier, we cannot guarantee solid performance if representations are of poor quality. However, learning high-quality setting is difficult because features classes easily overfit training dataset. In this work, propose mutual framework...
Several data augmentation methods deploy unlabeled-in-distribution (UID) to bridge the gap between training and inference of neural networks. However, these have clear limitations in terms availability UID dependence algorithms on pseudo-labels. Herein, we propose a method improve generalization both adversarial standard learning by using out-of-distribution (OOD) that are devoid abovementioned issues. We show how theoretically OOD each scenario complement our theoretical analysis with...