ICCV Presentation Video: DisUnknown: Distilling Unknown Factors for Disentanglement Learning
Автор: ICT Vision and Graphics Lab
Загружено: 2021-10-13
Просмотров: 644
Disentangling data into interpretable and independent factors is critical for controllable generation tasks. With the availability of labeled data, supervision can help enforce the separation of specific factors as expected. However, it is often expensive or even impossible to label every single factor to achieve fully supervised disentanglement. In this paper, we adopt a general setting where all factors that are hard to label or identify are encapsulated as a single unknown factor. Under this setting, we propose a flexible weakly-supervised multi-factor disentanglement framework DisUnknown, which Distills Unknown factors for enabling multi-conditional generation regarding both labeled and unknown factors. Specifically, a two-stage training approach is adopted to first disentangle the unknown factor with an effective and robust training method, and then train the final generator with the proper disentanglement of all labeled factors utilizing the unknown distillation. To demonstrate the generalization capacity and scalability of our method, we evaluate it on multiple benchmark datasets qualitatively and quantitatively and further apply it to various real-world applications on complicated datasets.
http://vgl.ict.usc.edu/
http://www.ict.usc.edu/
Доступные форматы для скачивания:
Скачать видео mp4
-
Информация по загрузке:
