Related papers: FlipDA: Effective and Robust Data Augmentation for…
As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for…
Augmenting data in image space (eg. flipping, cropping etc) and activation space (eg. dropout) are being widely used to regularise deep neural networks and have been successfully applied on several computer vision tasks. Unlike previous…
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…
Data augmentation is a commonly used approach to improving the generalization of deep learning models. Recent works show that learned data augmentation policies can achieve better generalization than hand-crafted ones. However, most of…
Data augmentation is an effective way to improve the performance of many neural text generation models. However, current data augmentation methods need to define or choose proper data mapping functions that map the original samples into the…
A critical bottleneck in supervised machine learning is the need for large amounts of labeled data which is expensive and time consuming to obtain. However, it has been shown that a small amount of labeled data, while insufficient to…
Training accurate intent classifiers requires labeled data, which can be costly to obtain. Data augmentation methods may ameliorate this issue, but the quality of the generated data varies significantly across techniques. We study the…
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…
A wide breadth of research has devised data augmentation approaches that can improve both accuracy and generalization performance for neural networks. However, augmented data can end up being far from the clean training data and what is the…
With the continuous development of natural language processing (NLP) technology, text classification tasks have been widely used in multiple application fields. However, obtaining labeled data is often expensive and difficult, especially in…
Data augmentation is a widely used technique to address the problem of text classification when there is a limited amount of training data. Recent work often tackles this problem using large language models (LLMs) like GPT3 that can…
We present CoDa (Constrained Generation based Data Augmentation), a controllable, effective, and training-free data augmentation technique for low-resource (data-scarce) NLP. Our approach is based on prompting off-the-shelf…
Electronic nose has been proven to be effective in alternative herbal medicine classification, but due to the nature of supervised learning, previous research heavily relies on the labelled training data, which are time-costly and…
Prior work on language models (LMs) shows that training on a large number of diverse tasks improves few-shot learning (FSL) performance on new tasks. We take this to the extreme, automatically extracting 413,299 tasks from internet tables -…
Despite strong performance in data-rich regimes, deep learning often underperforms in the data-scarce settings common in practice. While foundation models (FMs) trained on massive datasets demonstrate strong generalization by extracting…
AutoAugment has sparked an interest in automated augmentation methods for deep learning models. These methods estimate image transformation policies for train data that improve generalization to test data. While recent papers evolved in the…
Training a linear classifier or lightweight model on top of pretrained vision model outputs, so-called 'frozen features', leads to impressive performance on a number of downstream few-shot tasks. Currently, frozen features are not modified…
This paper introduces a novel dual-region augmentation approach designed to reduce reliance on large-scale labeled datasets while improving model robustness and adaptability across diverse computer vision tasks, including source-free domain…
In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping,…
This study introduces a novel data augmentation technique, ADLDA, aimed at mitigating the negative impact of data distribution shifts caused by the data augmentation process in computer vision task. ADLDA partitions augmented data into…