Search Results for author: Shaoan Xie

Found 12 papers, 3 papers with code

Causal Representation Learning from Multiple Distributions: A General Setting

no code implementations7 Feb 2024 Kun Zhang, Shaoan Xie, Ignavier Ng, Yujia Zheng

We show that under the sparsity constraint on the recovered graph over the latent variables and suitable sufficient change conditions on the causal influences, interestingly, one can recover the moralized graph of the underlying directed acyclic graph, and the recovered latent variables and their relations are related to the underlying causal model in a specific, nontrivial way.

Representation Learning

DreamInpainter: Text-Guided Subject-Driven Image Inpainting with Diffusion Models

no code implementations5 Dec 2023 Shaoan Xie, Yang Zhao, Zhisheng Xiao, Kelvin C. K. Chan, Yandong Li, Yanwu Xu, Kun Zhang, Tingbo Hou

Our extensive experiments demonstrate the superior performance of our method in terms of visual quality, identity preservation, and text control, showcasing its effectiveness in the context of text-guided subject-driven image inpainting.

Image Inpainting

Partial Identifiability for Domain Adaptation

no code implementations10 Jun 2023 Lingjing Kong, Shaoan Xie, Weiran Yao, Yujia Zheng, Guangyi Chen, Petar Stojanov, Victor Akinwande, Kun Zhang

In general, without further assumptions, the joint distribution of the features and the label is not identifiable in the target domain.

Unsupervised Domain Adaptation

Advancing Counterfactual Inference through Nonlinear Quantile Regression

no code implementations9 Jun 2023 Shaoan Xie, Biwei Huang, Bin Gu, Tongliang Liu, Kun Zhang

Traditional counterfactual inference, under Pearls' counterfactual framework, typically depends on having access to or estimating a structural causal model.

counterfactual Counterfactual Inference +2

Emerging Synergies in Causality and Deep Generative Models: A Survey

no code implementations29 Jan 2023 Guanglin Zhou, Shaoan Xie, GuangYuan Hao, Shiming Chen, Biwei Huang, Xiwei Xu, Chen Wang, Liming Zhu, Lina Yao, Kun Zhang

In the field of artificial intelligence (AI), the quest to understand and model data-generating processes (DGPs) is of paramount importance.

Causal Identification Fairness +1

SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model

no code implementations CVPR 2023 Shaoan Xie, Zhifei Zhang, Zhe Lin, Tobias Hinz, Kun Zhang

By contrast, multi-modal inpainting provides more flexible and useful controls on the inpainted content, \eg, a text prompt can be used to describe an object with richer attributes, and a mask can be used to constrain the shape of the inpainted object rather than being only considered as a missing area.

Image Inpainting Object +1

Adversarial Consistency for Single Domain Generalization in Medical Image Segmentation

no code implementations28 Jun 2022 Yanwu Xu, Shaoan Xie, Maxwell Reynolds, Matthew Ragoza, Mingming Gong, Kayhan Batmanghelich

An organ segmentation method that can generalize to unseen contrasts and scanner settings can significantly reduce the need for retraining of deep learning models.

Contrastive Learning Domain Generalization +5

Unaligned Image-to-Image Translation by Learning to Reweight

1 code implementation ICCV 2021 Shaoan Xie, Mingming Gong, Yanwu Xu, Kun Zhang

An essential yet restrictive assumption for unsupervised image translation is that the two domains are aligned, e. g., for the selfie2anime task, the anime (selfie) domain must contain only anime (selfie) face images that can be translated to some images in the other domain.

Translation Unsupervised Image-To-Image Translation

Box-Adapt: Domain-Adaptive Medical Image Segmentation using Bounding BoxSupervision

no code implementations19 Aug 2021 Yanwu Xu, Mingming Gong, Shaoan Xie, Kayhan Batmanghelich

In this paper, we propose a weakly supervised do-main adaptation setting, in which we can partially label newdatasets with bounding boxes, which are easier and cheaperto obtain than segmentation masks.

Domain Adaptation Image Segmentation +3

Learning Semantic Representations for Unsupervised Domain Adaptation

1 code implementation ICML 2018 Shaoan Xie, Zibin Zheng, Liang Chen, Chuan Chen

Prior domain adaptation methods address this problem through aligning the global distribution statistics between source domain and target domain, but a drawback of prior methods is that they ignore the semantic information contained in samples, e. g., features of backpacks in target domain might be mapped near features of cars in source domain.

Learning Semantic Representations Unsupervised Domain Adaptation

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