In this work, we connect two distinct concepts for unsupervised domain adaptation: feature distribution alignment between domains by utilizing the task-specific decision boundary [58] and the Wasserstein metric [73]. Our proposed sliced Wasserstein discrepancy (SWD) is designed to capture the natural notion of dissimilarity between the outputs of task-specific classifiers. It provides a geometrically meaningful guidance to detect target samples that are far from the support of the source and enables efficient distribution alignment in an end-to-end trainable fashion. In the experiments, we validate the effectiveness and genericness of our method on digit and sign recognition, image classification, semantic segmentation, and object detection.
We introduce GAUDI, a generative model capable of capturing the distribution of complex and realistic 3D scenes that can be rendered immersively from a moving camera. We tackle this challenging problem with a scalable yet powerful approach, where we first optimize a latent representation that disentangles radiance fields and camera poses. This latent representation is then used to learn a generative model that enables both unconditional and conditional generation of 3D scenes. Our model generalizes previous works that focus on single objects by removing the assumption that the camera pose distribution can be shared across samples. We show that GAUDI obtains state-of-the-art performance in the unconditional generative setting across multiple datasets and allows for conditional generation of 3D scenes given conditioning variables like sparse image observations or text that describes the scene.
Crosslinked ethylene vinyl acetate (EVA) resin is the preferred material for encapsulation of photovoltaic (PV) modules. Yet, profiling the spatial homogeneity of crosslinking in a quantitative and non-destructive way still remains a challenge. With the aid of reference techniques and using carefully prepared and well characterized model systems we have developed a protocol for Raman microscopy, which can determine the degree of crosslinking in EVA sheets in a quantitative manner. The new method has then been applied to characterize inhomogeneities with regard to crosslinking in EVA samples on various length scales, going down to a few μm. Finally, this method has been used to study crosslinking in EVA/glass laminates. The applicability and limitations of measuring crosslinking under glass was probed
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.