… a novel extension of the Wasserstein distance from probability … We also describe a statistical
learning bound for the loss. … apply the Wasserstein loss to a real world multi-label learning …

… In this section, we introduce the Wasserstein ground metric for the Wasserstein loss
function. A motivating example is presented to demonstrate the utility of the proposed model. …

… Wasserstein losses for continuous, semidiscrete and discrete distributions. Definition 1 (Minibatch
Wasserstein … We now state some basic properties for minibatch Wasserstein losses. All …

… to solve dictionary learning and NMF problems with a Wasserstein loss scale to problems …
a detailed presentation of our algorithms for Wasserstein (nonnegative) matrix factorization of …

… the Wasserstein loss for … Wasserstein distance as loss function in the learning. This is
motivated by miss-alignments in training data, which when using standard mean squared error loss …

… on the Wasserstein distance called Wasserstein Loss based … (CE), the Wasserstein loss
assigns different weights for one … (BCE) with Wasserstein distance to learn the detector con…

… Wasserstein loss function, as well as its convex relaxation that has an efficient algorithm for
computing the loss … hypothesis that the Wasserstein loss helps the learning model when the …

… usually include a domain invariant representation learning approach to measure and reduce
… Inspired by Wasserstein GAN, in this paper we propose a novel approach to learn domain …

… the loss function based on Wasserstein … learning, we try to add external information from
ConceptNet based on WGD model for semi-supervised learning and propose the Wasserstein …

Small objects in the airport scene, such as Persons and Vehicles, can lead to low accuracy
and robustness of the object detection task. To address the above problems, an improved …