相关论文: Does Data Augmentation Improve Generalization in N…

Data augmentation that introduces diversity into the input data has long been used in training deep learning models. It has demonstrated benefits in improving robustness and generalization, practically aligning well with other…

Manipulating data, such as weighting data examples or augmenting with new instances, has been increasingly used to improve model training. Previous work has studied various rule- or learning-based approaches designed for specific types of…

Label noise is common in large real-world datasets, and its presence harms the training process of deep neural networks. Although several works have focused on the training strategies to address this problem, there are few studies that…

Deep learning models tend not to be out-of-distribution robust primarily due to their reliance on spurious features to solve the task. Counterfactual data augmentations provide a general way of (approximately) achieving representations that…

We are concerned with learning models that generalize well to different \emph{unseen} domains. We consider a worst-case formulation over data distributions that are near the source domain in the feature space. Only using training data from…

This paper investigates methods for improving generative data augmentation for deep learning. Generative data augmentation leverages the synthetic samples produced by generative models as an additional dataset for classification with small…

Mixup is a popular data augmentation technique based on taking convex combinations of pairs of examples and their labels. This simple technique has been shown to substantially improve both the robustness and the generalization of the…

Model-Based Reinforcement Learning (RL) is widely believed to have the potential to improve sample efficiency by allowing an agent to synthesize large amounts of imagined experience. Experience Replay (ER) can be considered a simple kind of…

Neural language models (LMs) are arguably less data-efficient than humans from a language acquisition perspective. One fundamental question is why this human-LM gap arises. This study explores the advantage of grounded language acquisition,…

Data augmentation is an effective technique to improve the generalization of deep neural networks. However, previous data augmentation methods usually treat the augmented samples equally without considering their individual impacts on the…

Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters. To adapt to…

In many machine learning for healthcare tasks, standard datasets are constructed by amassing data across many, often fundamentally dissimilar, sources. But when does adding more data help, and when does it hinder progress on desired model…

Objective: The use of deep learning for electroencephalography (EEG) classification tasks has been rapidly growing in the last years, yet its application has been limited by the relatively small size of EEG datasets. Data augmentation,…

When large language models are aligned via supervised fine-tuning, they may encounter new factual information that was not acquired through pre-training. It is often conjectured that this can teach the model the behavior of hallucinating…

Generalization is the ability of a model to predict on unseen domains and is a fundamental task in machine learning. Several generalization bounds, both theoretical and empirical have been proposed but they do not provide tight bounds .In…

The real-time segmentation of drivable areas plays a vital role in accomplishing autonomous perception in cars. Recently there have been some rapid strides in the development of image segmentation models using deep learning. However, most…

Over-parameterized deep neural networks have proven to be able to learn an arbitrary dataset with 100$\%$ training accuracy. Because of a risk of overfitting and computational cost issues, we cannot afford to increase the number of network…

There have been growing concerns regarding the out-of-domain generalization ability of natural language processing (NLP) models, particularly in question-answering (QA) tasks. Current synthesized data augmentation methods for QA are…

Machine learning models can reach high performance on benchmark natural language processing (NLP) datasets but fail in more challenging settings. We study this issue when a pre-trained model learns dataset artifacts in natural language…

That shared features between train and test data are required for generalisation in artificial neural networks has been a common assumption of both proponents and critics of these models. Here, we show that convolutional architectures avoid…