Qi Dou

Domain Generalization via Model-Agnostic Learning of Semantic Features

2019 · arXiv (Cornell University)

Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data such that it …

Harmonizing Transferability and Discriminability for Adapting Object Detectors

2020 · arXiv (Cornell University)

Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection pipeline. Whilst adversarial adaptation significantly enhances the transferability of feature representations, …