arXiv:2202.09134v5 Announce Type: replace-cross 
Abstract: We provide universality results that quantify how data augmentation affects the variance and limiting distribution of estimates through simple surrogates, and analyze several specific models in detail. The results confirm some observations made in machine learning practice, but also lead to unexpected findings: Data augmentation may increase rather than decrease the uncertainty of estimates, such as the empirical prediction risk. It can act as a regularizer, but fails to do so in certain high-dimensional problems, and it may shift the double-descent peak of an empirical risk. Overall, the analysis shows that several properties data augmentation has been attributed with are not either true or false, but rather depend on a combination of factors -- notably the data distribution, the properties of the estimator, and the interplay of sample size, number of augmentations, and dimension. As our main theoretical tool, we develop an adaptation of Lindeberg's technique for block dependence. The resulting universality regime may be Gaussian or non-Gaussian.

أظهرت دراسة حديثة نتائج عالمية تتعلق بتأثير زيادة البيانات على التباين والتوزيع المحدود للتقديرات، مما يشير إلى أنها قد تزيد من عدم اليقين بدلاً من تقليله في بعض الأحيان. تسلط التحليل الضوء على أن فعالية زيادة البيانات تعتمد على عوامل متعددة، بما في ذلك توزيع البيانات وخصائص المُقدّر.

Un estudio reciente ha revelado resultados de universalidad sobre el impacto de la augmentación de datos en la varianza y la distribución límite de las estimaciones, indicando que a veces puede aumentar la incertidumbre en lugar de disminuirla. El análisis destaca que la efectividad de la augmentación de datos depende de varios factores, incluyendo la distribución de datos y las propiedades del estimador.

Une étude récente a révélé des résultats de universalité concernant l'impact de l'augmentation des données sur la variance et la distribution limite des estimations, indiquant qu'elle peut parfois augmenter l'incertitude plutôt que de la diminuer. L'analyse souligne que l'efficacité de l'augmentation des données dépend de divers facteurs, y compris la distribution des données et les propriétés de l'estimateur.

A recent study has revealed universality results regarding the impact of data augmentation on the variance and limiting distribution of estimates, indicating that it can sometimes increase uncertainty rather than decrease it. The analysis highlights that the effectiveness of data augmentation is contingent on various factors, including data distribution and estimator properties.

Gaussian and Non-Gaussian Universality of Data Augmentation

arXiv:2512.03370v1 Announce Type: new 
Abstract: We introduce ShelfGaussian, an open-vocabulary multi-modal Gaussian-based 3D scene understanding framework supervised by off-the-shelf vision foundation models (VFMs). Gaussian-based methods have demonstrated superior performance and computational efficiency across a wide range of scene understanding tasks. However, existing methods either model objects as closed-set semantic Gaussians supervised by annotated 3D labels, neglecting their rendering ability, or learn open-set Gaussian representations via purely 2D self-supervision, leading to degraded geometry and limited to camera-only settings. To fully exploit the potential of Gaussians, we propose a Multi-Modal Gaussian Transformer that enables Gaussians to query features from diverse sensor modalities, and a Shelf-Supervised Learning Paradigm that efficiently optimizes Gaussians with VFM features jointly at 2D image and 3D scene levels. We evaluate ShelfGaussian on various perception and planning tasks. Experiments on Occ3D-nuScenes demonstrate its state-of-the-art zero-shot semantic occupancy prediction performance. ShelfGaussian is further evaluated on an unmanned ground vehicle (UGV) to assess its in the-wild performance across diverse urban scenarios. Project website: https://lunarlab-gatech.github.io/ShelfGaussian/.

تم تقديم ShelfGaussian كإطار لفهم المشاهد ثلاثية الأبعاد يعتمد على Gaussian متعدد الوسائط وذو مفردات مفتوحة، مستفيدًا من نماذج رؤية الأساس المتاحة لتحسين الأداء والكفاءة في مجموعة متنوعة من مهام فهم المشهد. يتناول هذا الإطار قيود الأساليب الحالية من خلال تمكين Gaussian من استعلام الميزات من عدة أنواع من المستشعرات وتحسينها على مستويات 2D و3D.

ShelfGaussian se ha introducido como un marco de comprensión de escenas 3D basado en Gaussianos multimodales y de vocabulario abierto, aprovechando modelos de visión de fundación disponibles para mejorar el rendimiento y la eficiencia en diversas tareas de comprensión de escenas. Este marco aborda las limitaciones de los métodos existentes al permitir que los Gaussianos consulten características de múltiples modalidades de sensores y optimizarlos tanto a niveles 2D como 3D.

ShelfGaussian a été introduit comme un cadre de compréhension de scène 3D basé sur des Gaussiens multi-modaux et à vocabulaire ouvert, tirant parti de modèles de fondation visuels disponibles pour améliorer la performance et l'efficacité dans diverses tâches de compréhension de scène. Ce cadre répond aux limitations des méthodes existantes en permettant aux Gaussiens d'interroger des caractéristiques de multiples modalités de capteurs et en les optimisant à la fois aux niveaux 2D et 3D.

ShelfGaussian has been introduced as an open-vocabulary multi-modal Gaussian-based framework for 3D scene understanding, leveraging off-the-shelf vision foundation models to enhance performance and efficiency in various scene understanding tasks. This framework addresses limitations of existing methods by enabling Gaussians to query features from multiple sensor modalities and optimizing them at both 2D and 3D levels.

Gaussian and Non-Gaussian Universality of Data Augmentation

Was this article worth reading? Share it

LucidQuery AI

Augmeta

Omnifact