MM2020 - Adversarial Bipartite Graph Learning for Video Domain Adaptation
To appear in ACM Multimedia 2020
Yadan Luo†, Zi Huang†, Zijian Wang†, Zheng Zhang‡, Mahsa Baktashmotlagh†
†The University of Queensland
‡ Bio-Computing Research Center, Harbin Institute of Technology, Shenzhen
Source Code: https://github.com/Luoyadan/MM2020_ABG
In this work, we propose a bipartite graph learning framework for unsupervised and semi-supervised video domain adaptation tasks. Different the existing approaches which learn domain-invariant features,we construct a domain-agnostic classifier by leveraging the bipartite graphs to combine the similar source and target features at the training and test time, which helps with reducing the exposure bias. Experiments evidence effectiveness of our proposed approach over the state-of-the-art methods, improving their performance by up to 39.6% in a semi-supervised setting.