16 citations · 19 across the 13 of their papers we have counts for
15 papers
Binding Multiple Modalities via Multimodal Wasserstein Barycenter
Xiaole Tang, Jiayi Xu, Xiang Gu +2
Multimodal learning beyond two modalities commonly leverages a specific modality (e.g., text) to bind other modalities. However, how to establish a more balanced representation spa…
Coupled Optimal Transport with Landmark Constraints
Xiang Gu, Jian Sun, Zongben Xu
Existing optimal transport (OT) models primarily seek an OT map or plan between distributions by minimizing a prescribed transport cost or distortion. However, minimizing transport…
A Residual-Shell-Based Lower Bound for Ollivier-Ricci Curvature
Xiang Gu, Huichun Zhang, Jian Sun
Ollivier-Ricci curvature (ORC), defined via the Wasserstein distance that captures rich geometric information, has received growing attention in both theory and applications. Howev…
Learning Continuous Wasserstein Barycenter Space for Generalized All-in-One Image Restoration
Xiaole Tang, Xiaoyi He, Jiayi Xu +2
Despite substantial advances in all-in-one image restoration for addressing diverse degradations within a unified model, existing methods remain vulnerable to out-of-distribution d…
Generating transition states of chemical reactions via distance-geometry-based flow matching
Yufei Luo, Xiang Gu, Jian Sun
Transition states (TSs) are crucial for understanding reaction mechanisms, yet their exploration is limited by the complexity of experimental and computational approaches. Here we…
BaryIR: Learning Multi-Source Unified Representation in Continuous Barycenter Space for Generalizable All-in-One Image Restoration
Xiaole Tang, Xiaoyi He, Xiang Gu +1
Despite remarkable advances made in all-in-one image restoration (AIR) for handling different types of degradations simultaneously, existing methods remain vulnerable to out-of-dis…
Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport
Taoran Zheng, Yan Yang, Xing Li +3
Medical image reconstruction from measurement data is a vital but challenging inverse problem. Deep learning approaches have achieved promising results, but often requires paired m…
Joint Velocity-Growth Flow Matching for Single-Cell Dynamics Modeling
Dongyi Wang, Yuanwei Jiang, Zhenyi Zhang +3
Learning the underlying dynamics of single cells from snapshot data has gained increasing attention in scientific and machine learning research. The destructive measurement techniq…
GMapLatent: Geometric Mapping in Latent Space
Wei Zeng, Xuebin Chang, Jianghao Su +3
Cross-domain generative models based on encoder-decoder AI architectures have attracted much attention in generating realistic images, where domain alignment is crucial for generat…
Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration
Xiaole Tang, Xiang Gu, Xiaoyi He +2
All-in-one image restoration has emerged as a practical and promising low-level vision task for real-world applications. In this context, the key issue lies in how to deal with dif…
Prototypical Partial Optimal Transport for Universal Domain Adaptation
Yucheng Yang, Xiang Gu, Jian Sun
Universal domain adaptation (UniDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain without requiring the same label sets of both domains. The…
Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration
Xiaole Tang, Xin Hu, Xiang Gu +1
Deep learning-based image restoration methods generally struggle with faithfully preserving the structures of the original image. In this work, we propose a novel Residual-Conditio…
Optimal Transport-Guided Conditional Score-Based Diffusion Models
Xiang Gu, Liwei Yang, Jian Sun +1
Conditional score-based diffusion model (SBDM) is for conditional generation of target data with paired data as condition, and has achieved great success in image translation. Howe…
Generalized Semantic Segmentation by Self-Supervised Source Domain Projection and Multi-Level Contrastive Learning
Liwei Yang, Xiang Gu, Jian Sun
Deep networks trained on the source domain show degraded performance when tested on unseen target domain data. To enhance the model's generalization ability, most existing domain g…
Keypoint-Guided Optimal Transport: Models, Algorithms, and Applications
Xiang Gu, Yucheng Yang, Wei Zeng +2
Existing Optimal Transport (OT) methods mainly derive the optimal transport plan/matching under the criterion of transport cost/distance minimization, which may cause incorrect mat…