A Fast Proximal Point Method for Computing Exact Wasserstein Distance

171 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

UFO: A UniFied TransfOrmer for Vision-Language Representation Learning (2021, methodology): “The image and text tokens are first connected through solving an optimal transport problem by the inexact proximal point method [49].”
ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision (2021, methodology): “(2019), we design word patch alignment (WPA) that computes the alignment score between two subsets of z: z|t (textual subset) and z|v (visual subset), using the inexact proximal point method for optimal transports (IPOT) (Xie et al., 2020).”
Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training (2021, methodology): “Our VLA loss optimize the Optimal Transport (OT) distance approximated by IPOT [42].”
Large-scale Multi-modal Pre-trained Models: A Comprehensive Survey (2023, methodology): “● Word-region alignment (WRA) is used in UNITER[18] which targets, at explicitly achieves the finegrained alignment between the multi-modal inputs via optimal transport (OT)[115].”
Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints (2020, methodology): “for Optimal Transport (IPOT) (Xie et al., 2018) as an approximation.”