Expanding Large Pre-Trained Unimodal Models With Multimodal Information Injection for Image-Text Multimodal Classification

no code implementations • CVPR 2022 • Tao Liang, Guosheng Lin, Mingyang Wan, Tianrui Li, Guojun Ma, Fengmao Lv

Through the proposed MI2P unit, we can inject the language information into the vision backbone by attending the word-wise textual features to different visual channels, as well as inject the visual information into the language backbone by attending the channel-wise visual features to different textual words.

Modeling Techniques for Machine Learning Fairness: A Survey

no code implementations • 4 Nov 2021 • Mingyang Wan, Daochen Zha, Ninghao Liu, Na Zou

Machine learning models are becoming pervasive in high-stakes applications.

BIG-bench Machine Learning Decision Making +2

Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learning

1 code implementation • 16 Sep 2020 • Daochen Zha, Kwei-Herng Lai, Mingyang Wan, Xia Hu

Specifically, existing strategies have been focused on making the top instances more likely to be anomalous based on the feedback.

Anomaly Detection reinforcement-learning +2