Related papers: Implicit Counterfactual Data Augmentation for Robu…
We present a new technique to enhance the robustness of imitation learning methods by generating corrective data to account for compounding errors and disturbances. While existing methods rely on interactive expert labeling, additional…
While deep learning models have shown remarkable performance in various tasks, they are susceptible to learning non-generalizable spurious features rather than the core features that are genuinely correlated to the true label. In this…
Invariant Contrastive Learning (ICL) methods have achieved impressive performance across various domains. However, the absence of latent space representation for distortion (augmentation)-related information in the latent space makes ICL…
Data augmentation (DA) is an essential technique for training state-of-the-art deep learning systems. In this paper, we empirically show data augmentation might introduce noisy augmented examples and consequently hurt the performance on…
Adversarial images are designed to mislead deep neural networks (DNNs), attracting great attention in recent years. Although several defense strategies achieved encouraging robustness against adversarial samples, most of them fail to…
Recent years have seen the introduction of a range of methods for post-hoc explainability of image classifier predictions. However, these post-hoc explanations may not always be faithful to classifier predictions, which poses a significant…
Deep learning-based methods have reached state of the art performances, relying on large quantity of available data and computational power. Such methods still remain highly inappropriate when facing a major open machine learning problem,…
Being widely used in learning unbiased visual question answering (VQA) models, Data Augmentation (DA) helps mitigate language biases by generating extra training samples beyond the original samples. While today's DA methods can generate…
Offline data are both valuable and practical resources for teaching robots complex behaviors. Ideally, learning agents should not be constrained by the scarcity of available demonstrations, but rather generalize beyond the training…
Recently, utilizing large language models (LLMs) for metaphor detection has achieved promising results. However, these methods heavily rely on the capabilities of closed-source LLMs, which come with relatively high inference costs and…
Contrastive learning (CL), a self-supervised learning approach, can effectively learn visual representations from unlabeled data. Given the CL training data, generative models can be trained to generate synthetic data to supplement the real…
This study addresses the actual behavior of the credit-card fraud detection environment where financial transactions containing sensitive data must not be amassed in an enormous amount to conduct learning. We introduce a new adaptive…
Data augmentation is an effective way to diversify corpora in machine translation, but previous methods may introduce semantic inconsistency between original and augmented data because of irreversible operations and random subword sampling…
Data augmentation has been proven effective for training high-accuracy convolutional neural network classifiers by preventing overfitting. However, building deep neural networks in real-world scenarios requires not only high accuracy on…
Learning from class imbalanced datasets poses challenges for many machine learning algorithms. Many real-world domains are, by definition, class imbalanced by virtue of having a majority class that naturally has many more instances than its…
In attempts to produce ML models less reliant on spurious patterns in NLP datasets, researchers have recently proposed curating counterfactually augmented data (CAD) via a human-in-the-loop process in which given some documents and their…
Self-supervised learning aims to learn a embedding space where semantically similar samples are close. Contrastive learning methods pull views of samples together and push different samples away, which utilizes semantic invariance of…
Data augmentation is a widely used technique and an essential ingredient in the recent advance in self-supervised representation learning. By preserving the similarity between augmented data, the resulting data representation can improve…
Contrastive learning demonstrates great promise for representation learning. Data augmentations play a critical role in contrastive learning by providing informative views of the data without necessitating explicit labels. Nonetheless, the…
As the representation capability of Pre-trained Language Models (PLMs) improve, there is growing concern that they will inherit social biases from unprocessed corpora. Most previous debiasing techniques used Counterfactual Data Augmentation…