Timezone: »

Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows
Chao Du · Tianbo Li · Tianyu Pang · Shuicheng YAN · Min Lin

Tue Jul 25 02:00 PM -- 04:30 PM (PDT) @ Exhibit Hall 1 #120
Event URL: https://github.com/duchao0726/Conditional-SWF »

Sliced-Wasserstein Flow (SWF) is a promising approach to nonparametric generative modeling but has not been widely adopted due to its suboptimal generative quality and lack of conditional modeling capabilities. In this work, we make two major contributions to bridging this gap. First, based on a pleasant observation that (under certain conditions) the SWF of joint distributions coincides with those of conditional distributions, we propose Conditional Sliced-Wasserstein Flow (CSWF), a simple yet effective extension of SWF that enables nonparametric conditional modeling. Second, we introduce appropriate inductive biases of images into SWF with two techniques inspired by local connectivity and multiscale representation in vision research, which greatly improve the efficiency and quality of modeling images. With all the improvements, we achieve generative performance comparable with many deep parametric generative models on both conditional and unconditional tasks in a purely nonparametric fashion, demonstrating its great potential.

Author Information

Chao Du (Sea AI Lab)
Tianbo Li (SAIL)
Tianyu Pang (Sea AI Lab)


Shuicheng YAN
Min Lin (Sea AI Lab)

More from the Same Authors