相关论文: Data augmentation with Mobius transformations

Despite substantial progress in the field of deep learning, overfitting persists as a critical challenge, and data augmentation has emerged as a particularly promising approach due to its capacity to enhance model generalization in various…

Data augmentation has been pivotal in successfully training deep learning models on classification tasks over the past decade. An important subclass of data augmentation techniques - which includes both label smoothing and Mixup - involves…

Data augmentation is used extensively to improve model generalisation. However, reliance on external libraries to implement augmentation methods introduces a vulnerability into the machine learning pipeline. It is well known that backdoors…

Robot learning methods have the potential for widespread generalization across tasks, environments, and objects. However, these methods require large diverse datasets that are expensive to collect in real-world robotics settings. For robot…

Though data augmentation has become a standard component of deep neural network training, the underlying mechanism behind the effectiveness of these techniques remains poorly understood. In practice, augmentation policies are often chosen…

Deep neural networks have achieved impressive performance in a wide variety of medical imaging tasks. However, these models often fail on data not used during training, such as data originating from a different medical centre. How to…

Data augmentation has recently seen increased interest in graph machine learning given its demonstrated ability to improve model performance and generalization by added training data. Despite this recent surge, the area is still relatively…

Recent advances in unsupervised learning have demonstrated the ability of large vision models to achieve promising results on downstream tasks by pre-training on large amount of unlabelled data. Such pre-training techniques have also been…

The translation equivariance of convolutional layers enables convolutional neural networks to generalize well on image problems. While translation equivariance provides a powerful inductive bias for images, we often additionally desire…

Performance is a critical challenge in mobile image processing. Given a reference imaging pipeline, or even human-adjusted pairs of images, we seek to reproduce the enhancements and enable real-time evaluation. For this, we introduce a new…

Data-Augmentation (DA) is known to improve performance across tasks and datasets. We propose a method to theoretically analyze the effect of DA and study questions such as: how many augmented samples are needed to correctly estimate the…

Learning in weight spaces, where neural networks process the weights of other deep neural networks, has emerged as a promising research direction with applications in various fields, from analyzing and editing neural fields and implicit…

Computer vision has flourished in recent years thanks to Deep Learning advancements, fast and scalable hardware solutions and large availability of structured image data. Convolutional Neural Networks trained on supervised tasks with…

Generalization to unseen real-world scenarios for robot manipulation requires exposure to diverse datasets during training. However, collecting large real-world datasets is intractable due to high operational costs. For robot learning to…

In semi-supervised semantic segmentation (SSSS), data augmentation plays a crucial role in the weak-to-strong consistency regularization framework, as it enhances diversity and improves model generalization. Recent strong augmentation…

Data augmentation, a technique in which a training set is expanded with class-preserving transformations, is ubiquitous in modern machine learning pipelines. In this paper, we seek to establish a theoretical framework for understanding data…

Deep learning approaches have become the standard solution to many problems in computer vision and robotics, but obtaining sufficient training data in high enough quality is challenging, as human labor is error prone, time consuming, and…

Deep learning models can perform well when evaluated on images from the same distribution as the training set. However, applying small perturbations in the forms of noise, artifacts, occlusions, blurring, etc. to a model's input image and…

Deep learning techniques involving image processing and data analysis are constantly evolving. Many domains adapt these techniques for object segmentation, instantiation and classification. Recently, agricultural industries adopted those…

Data augmentation techniques, such as simple image transformations and combinations, are highly effective at improving the generalization of computer vision models, especially when training data is limited. However, such techniques are…