Dual Metric Discriminator for Open Set Video Domain Adaptation
Yatian Wang, Xiaolin Song, Yezhen Wang, Pengfei Xu, Runbo Hu, Hua Chai
Abstract
Existing video domain adaptation methods focus on addressing closed set problems. However, it is nearly impossible to guarantee different domains share exactly the same set of categories in realistic scenarios. Hence, open set video domain adaptation (OSVDA) problem, which involves unknown categories, has achieved increasingly close attention. In this paper, we propose a seminal framework, which involves spatial and temporal information to address OSVDA problem. Besides, we design a novel discrimination module, i.e., Dual Metric Discriminator (DMD), to separate known and unknown categories based on implicit and explicit similarity metrics. We conduct comprehensive experiments on several benchmarks and achieve state-of-the-art performance with 40.4%, 33.7%, and 79.2% accuracy on UCF to HMDB, HMDB to UCF, and Kinetics to UCF scenarios respectively.
BibTeX
@inproceedings{icassp2021_dualmetricdiscri,
title = {Dual Metric Discriminator for Open Set Video Domain Adaptation},
author = {Yatian Wang and Xiaolin Song and Yezhen Wang and Pengfei Xu and Runbo Hu and Hua Chai},
booktitle = {ICASSP 2021},
year = {2021}
}