Ngai‐Man Cheung

Simultaneous Low-rank Component and Graph Estimation for High-dimensional Graph Signals: Application to Brain Imaging

2016 · arXiv (Cornell University)

We propose an algorithm to uncover the intrinsic low-rank component of a high-dimensional, graph-smooth and grossly-corrupted dataset, under the situations that the underlying graph is unknown. Based on a model with a low-rank component plus …

Deep neural networks on graph signals for brain imaging analysis

2017 · arXiv (Cornell University)

Brain imaging data such as EEG or MEG are high-dimensional spatiotemporal data often degraded by complex, non-Gaussian noise. For reliable analysis of brain imaging data, it is important to extract discriminative, low-dimensional intrinsic representation of …

Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?

2022 · arXiv (Cornell University)

This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). Contemporary findings addressing this thesis statement take dichotomous standpoints: Muller et al. (2019) and Shen et al. (2021b). Critically, there is no …

Are Anomaly Scores Telling the Whole Story? A Benchmark for Multilevel Anomaly Detection

2024 · arXiv (Cornell University)

Anomaly detection (AD) is a machine learning task that identifies anomalies by learning patterns from normal training data. In many real-world scenarios, anomalies vary in severity, from minor anomalies with little risk to severe abnormalities …