Interpolating between points is a problem connected simultaneously with finding geodesics and study of generative models. In the case of geodesics, we search for the curves with the shortest length, while in the case ...
详细信息
Interpolating between points is a problem connected simultaneously with finding geodesics and study of generative models. In the case of geodesics, we search for the curves with the shortest length, while in the case of generative models, we typically apply linear interpolation in the latent space. However, this interpolation uses implicitly the fact that Gaussian is unimodal. Thus, the problem of interpolating in the case when the latent density is non-Gaussian is an open problem. In this article, we present a general and unified approach to interpolation, which simultaneously allows us to search for geodesics and interpolating curves in latent space in the case of arbitrary density. Our results have a strong theoretical background based on the introduced quality measure of an interpolating curve. In particular, we show that maximizing the quality measure of the curve can be equivalently understood as a search of geodesic for a certain redefinition of the Riemannian metric on the space. We provide examples in three important cases. First, we show that our approach can be easily applied to finding geodesics on manifolds. Next, we focus our attention in finding interpolations in pretrained generative models. We show that our model effectively works in the case of arbitrary density. Moreover, we can interpolate in the subset of the space consisting of data possessing a given feature. The last case is focused on finding interpolation in the space of chemical compounds.
Buildings consume around 40% of the total global energy consumption, while within the building, the HVAC systems are the most energy-hungry systems responsible for more than half of the total building's energy con...
详细信息
Mixup is a powerful data augmentation strategy that has been shown to improve the generalization and adversarial robustness of machinelearning classifiers, particularly in computer vision applications. Despite its si...
详细信息
Mixup is a powerful data augmentation strategy that has been shown to improve the generalization and adversarial robustness of machinelearning classifiers, particularly in computer vision applications. Despite its simplicity and effectiveness, the impact of Mixup on the fairness of a model has not been thoroughly investigated yet. In this paper, we demonstrate that Mixup can perpetuate or even exacerbate bias presented in the training set. We provide insight to understand the reasons behind this behavior and propose GBMix, a group-balanced Mixup strategy to train fair classifiers. It groups the dataset based on their attributes and balances the Mixup ratio between the groups. Through the reorganization and balance of Mixup among groups, GBMix effectively enhances both average and worst-case accuracy concurrently. We empirically show that GBMix effectively mitigates bias in the training set and reduces the performance gap between groups. This effect is observed across a range of datasets and networks, and GBMix outperforms all the state-of-the-art methods.
We consider the problem of sequential change detection under minimal assumptions on the distribution generating the stream of observations. Formally, our goal is to design a scheme for detecting any changes in a param...
We consider the problem of sequential change detection under minimal assumptions on the distribution generating the stream of observations. Formally, our goal is to design a scheme for detecting any changes in a parameter or functional θ of the data stream distribution that has small detection delay, but guarantees control on the frequency of false alarms in the absence of changes. We describe a simple reduction from sequential change detection to sequential estimation using confidence sequences (CSs): begin a new level-(1 − α) CS at each time step, and proclaim a change as soon as the intersection of all active CSs becomes empty. We prove that the average run length of our scheme is at least 1/α, resulting in a change detection scheme with minimal structural assumptions (thus allowing for possibly dependent observations, and nonparametric distribution classes), but strong guarantees. We also describe an interesting parallel with Lorden's reduction from change detection to sequential testing and connections to the recent "e-detector" framework. Copyright 2024 by the author(s)
This study employs three advanced gradient boosting machinelearning algorithms to assess potential disparities in healthcare delivery. We specifically investigate which factors contribute to a patient's timely di...
详细信息
Recent methods, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS), have demonstrated remarkable capabilities in novel view synthesis. However, despite their success in producing high-quality image...
详细信息
Speech recognition based mobile device applications are gaining popularity due to their ease of use, flexibility as well as ability to provide hands-free access to device features and functions for persons without han...
详细信息
Due to the vast array of NeRF-based techniques, the representation power of Neural Radiance Fields (NeRF) has been quickly rising in recent years. However, it is still difficult to offer fresh perspectives for user-co...
详细信息
Due to the vast array of NeRF-based techniques, the representation power of Neural Radiance Fields (NeRF) has been quickly rising in recent years. However, it is still difficult to offer fresh perspectives for user-controlled geometry alterations with current techniques;instead, they restrict edits to those that were observed during training or to particular regions chosen by the provider. In this paper, we present NeRFlex, Flexible Neural Radiance Fields with Diffeomorphic Deformation, which lets users process geometry completely unrestricted by using radiance field deformation. Given a condition with a specific viewpoint, a conditional score function is estimated using diffusion time steps. The deformation between the radiance fields before and after an edit is then generated by the score function and the initial radiance field. To guarantee topology preservation, invertibility, and smooth transformation, diffeomorphic constraints are provided to the deformation field. Experiments on various objects demonstrate NeRFlex's ability to generate flexible deformations and high-quality novel views after geometry edits, which were never observed in the training data. Continuous deformation along the pathway leading to the deformed object is also obtained by diffeomorphism decomposition.
In the realm of fashion object detection and segmentation for online shopping images, existing state-of-the-art fashion parsing models encounter limitations, particularly when exposed to non-model-worn apparel and clo...
详细信息
ISBN:
(纸本)9798350359329;9798350359312
In the realm of fashion object detection and segmentation for online shopping images, existing state-of-the-art fashion parsing models encounter limitations, particularly when exposed to non-model-worn apparel and close-up shots. To address these failures, we introduce FashionFail;a new fashion dataset with e-commerce images for object detection and segmentation. The dataset is efficiently curated using our novel annotation tool that leverages recent foundation models. The primary objective of FashionFail is to serve as a test bed for evaluating the robustness of models. Our analysis reveals the shortcomings of leading models, such as Attribute-Mask R-CNN and Fashionformer. Additionally, we propose a baseline approach using naive data augmentation to mitigate common failure cases and improve model robustness. Through this work, we aim to inspire and support further research in fashion item detection and segmentation for industrial applications. The dataset, annotation tool, code, and models are available at https://***/fashionfail/.
The vegetation height has been identified as a key biophysical parameter to justify the role of forests in the carbon cycle and ecosystem productivity. Therefore, consistent and large-scale forest height is essential ...
详细信息
ISBN:
(纸本)9798350360332;9798350360325
The vegetation height has been identified as a key biophysical parameter to justify the role of forests in the carbon cycle and ecosystem productivity. Therefore, consistent and large-scale forest height is essential for managing terrestrial ecosystems, mitigating climate change, and preventing biodiversity loss. Since spaceborne multispectral instruments, Light Detection and Ranging (LiDAR), and Synthetic Aperture Radar (SAR) have been widely used for large-scale earth observation for years, this paper explores the possibility of generating large-scale and high-accuracy forest heights with the synergy of the Sentinel-1, Sentinel- 2, and ICESat-2 data. A Forest Height Generative Adversarial Network (FH-GAN) is developed to retrieve forest height from Sentinel-1 and Sentinel-2 images sparsely supervised by the ICESat-2 data. This model is made up of a cascade forest height and coherence generator, where the output of the forest height generator is fed into the spatial discriminator to regularize spatial details, and the coherence generator is connected to a coherence discriminator to refine the vertical details. A progressive strategy further underpins the generator to boost the accuracy of multi-source forest height estimation. Results indicated that FH-GAN achieves the best RMSE of 2.10 m at a large scale compared with the LVIS reference and the best RMSE of 6.16 m compared with the ICESat-2 reference.
暂无评论