Shu Liu

Improving Calibration for Long-Tailed Recognition

2021 · arXiv (Cornell University)

Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to improve performance. But there is still the vital issue of miscalibration. To address …

A New Method of Data Fusion with PMU and SCADA Based on Branch Decomposition

2021 · 2021 IEEE Sustainable Power and Energy Conference (iSPEC)

The data fusion with synchro-phasor measurement unit (PMU) and supervisory control and data acquisition (SCADA) is the basis of improving the level of measurement and operational control of distribution network. In order to improve the …

BAL: Balancing Diversity and Novelty for Active Learning

2023 · arXiv (Cornell University)

The objective of Active Learning is to strategically label a subset of the dataset to maximize performance within a predetermined labeling budget. In this study, we harness features acquired through self-supervised learning. We introduce a …

Encoding of Algebraic Geometry Codes With Quasi-Linear Complexity O(NlogN)

2025 · IEEE Transactions on Information Theory

Fast encoding and decoding of codes have always been an important topic in coding theory as well as complexity theory. Although encoding is easier than decoding in general, designing an encoding algorithm of codes of …