相关论文: Generalization Gap in Data Augmentation: Insights …

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…

Deep learning has been extensively used in various fields, such as phase imaging, 3D imaging reconstruction, phase unwrapping, and laser speckle reduction, particularly for complex problems that lack analytic models. Its data-driven nature…

Physics-informed machine learning is gaining significant traction for enhancing statistical performance and sample efficiency through the integration of physical knowledge. However, current theoretical analyses often presume complete prior…

Robotics applications in urban environments are subject to obstacles that exhibit specular reflections hampering autonomous navigation. On the other hand, these reflections are highly polarized and this extra information can successfully be…

Systematic generalization is the ability to combine known parts into novel meaning; an important aspect of efficient human learning, but a weakness of neural network learning. In this work, we investigate how two well-known modeling…

Modern neural networks are over-parameterized and thus rely on strong regularization such as data augmentation and weight decay to reduce overfitting and improve generalization. The dominant form of data augmentation applies invariant…

Images of a scene observed under a variable illumination or with a variable optical aperture are not identical. Does a privileged representant exist? In which mathematical context? How to obtain it? The authors answer to such questions in…

In the ever-evolving landscape of social network advertising, the volume and accuracy of data play a critical role in the performance of predictive models. However, the development of robust predictive algorithms is often hampered by the…

The robustness of visual navigation policies trained through imitation often hinges on the augmentation of the training image-action pairs. Traditionally, this has been done by collecting data from multiple cameras, by using standard data…

Traditional data augmentation aims to increase the coverage of the input distribution by generating augmented examples that strongly resemble original samples in an online fashion where augmented examples dominate training. In this paper,…

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 plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…

This paper discusses the estimation of the generalization gap, the difference between generalization performance and training performance, for overparameterized models including neural networks. We first show that a functional variance, a…

Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthetic samples often…

In computer vision, it is well-known that a lack of data diversity will impair model performance. In this study, we address the challenges of enhancing the dataset diversity problem in order to benefit various downstream tasks such as…

The technique of data augmentation (DA) is often used in machine learning for regularization purposes to better generalize under i.i.d. settings. In this work, we present a unifying framework with topics in causal inference to make a case…

Deep neural networks trained with different architectures, objectives, and datasets have been reported to converge on similar visual representations. However, what remains unknown is which visual properties models actually converge on and…

In the rapidly evolving field of large language models (LLMs), data augmentation (DA) has emerged as a pivotal technique for enhancing model performance by diversifying training examples without the need for additional data collection. This…

Providing a human-understandable explanation of classifiers' decisions has become imperative to generate trust in their use for day-to-day tasks. Although many works have addressed this problem by generating visual explanation maps, they…

Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task. However, when tested on unseen data, the models may not perform well. Therefore, the models need to be…