ErGAN: Generative Adversarial Networks for Entity Resolution

no code implementations • 18 Dec 2020 • Jingyu Shao, Qing Wang, Asiri Wijesinghe, Erhard Rahm

Entity resolution targets at identifying records that represent the same real-world entity from one or more datasets.

Entity Resolution Generative Adversarial Network

Learning to Sample: an Active Learning Framework

no code implementations • 9 Sep 2019 • Jingyu Shao, Qing Wang, Fangbing Liu

However, current learning-based active learning approaches still require sufficient training data so as to generalize meta-learning models for active learning.

Active Learning Entity Resolution +2

Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions

no code implementations • NeurIPS 2016 • Ayan Chakrabarti, Jingyu Shao, Gregory Shakhnarovich

A single color image can contain many cues informative towards different aspects of local geometric structure.

Monocular Depth Estimation