Search Results for author: Jiaojiao Fan

Found 7 papers, 3 papers with code

RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance

no code implementations27 May 2024 Jiaojiao Fan, Haotian Xue, Qinsheng Zhang, Yongxin Chen

Motivated by this observation, we find that a rank-1 coefficient is not necessary and simplifies the controllable generation mechanism.

Image Generation Video Generation

Generating Synthetic Datasets by Interpolating along Generalized Geodesics

no code implementations12 Jun 2023 Jiaojiao Fan, David Alvarez-Melis

We compute these geodesics using a recent notion of distance between labeled datasets, and derive alternative interpolation schemes based on it: using either barycentric projections or optimal transport maps, the latter computed using recent neural OT methods.

Transfer Learning

Improved dimension dependence of a proximal algorithm for sampling

no code implementations20 Feb 2023 Jiaojiao Fan, Bo Yuan, Yongxin Chen

For instance, for strongly log-concave distributions, our method has complexity bound $\tilde\mathcal{O}(\kappa d^{1/2})$ without warm start, better than the minimax bound for MALA.

Variational Wasserstein gradient flow

1 code implementation4 Dec 2021 Jiaojiao Fan, Qinsheng Zhang, Amirhossein Taghvaei, Yongxin Chen

Wasserstein gradient flow has emerged as a promising approach to solve optimization problems over the space of probability distributions.

Neural Monge Map estimation and its applications

1 code implementation7 Jun 2021 Jiaojiao Fan, Shu Liu, Shaojun Ma, Haomin Zhou, Yongxin Chen

Monge map refers to the optimal transport map between two probability distributions and provides a principled approach to transform one distribution to another.

Image Inpainting Text-to-Image Generation

Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networks

2 code implementations8 Jul 2020 Jiaojiao Fan, Amirhossein Taghvaei, Yongxin Chen

Wasserstein Barycenter is a principled approach to represent the weighted mean of a given set of probability distributions, utilizing the geometry induced by optimal transport.

Cannot find the paper you are looking for? You can Submit a new open access paper.