DisUnknown: Distilling Unknown Factors for Disentanglement Learning
This addresses the challenge of achieving fully-supervised disentanglement in machine learning, particularly for controllable generation tasks, by providing a flexible solution that reduces labeling costs, though it is incremental as it builds on existing disentanglement methods.
The paper tackles the problem of disentangling data into interpretable factors for controllable generation when labeling all factors is impractical, by proposing DisUnknown, a weakly-supervised framework that distills unknown factors into a single representation, enabling multi-conditional generation with both labeled and unknown factors.
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.