Related papers: On the Effects of Artificial Data Modification
Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is possible in real-world use cases due to the diversity of…
Data augmentation has become a standard practice in software engineering to address limited or imbalanced data sets, particularly in specialized domains like test classification and bug detection where data can be scarce. Although…
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…
The embedding spaces of image models have been shown to encode a range of social biases such as racism and sexism. Here, we investigate specific factors that contribute to the emergence of these biases in Vision Transformers (ViT).…
State-of-the-art algorithms for many semantic visual tasks are based on the use of convolutional neural networks. These networks are commonly trained, and evaluated, on large annotated datasets of artifact-free high-quality images. In this…
Data augmentation (DA) enhances model generalization in computer vision but may introduce biases, impacting class accuracy unevenly. Our study extends this inquiry, examining DA's class-specific bias across various datasets, including those…
Machine learning models are susceptible to being misled by biases in training data that emphasize incidental correlations over the intended learning task. In this study, we demonstrate the impact of data bias on the performance of a machine…
The development of technologies for easily and automatically falsifying video has raised practical questions about people's ability to detect false information online. How vulnerable are people to deepfake videos? What technologies can be…
Mixup is a data augmentation technique that relies on training using random convex combinations of data points and their labels. In recent years, Mixup has become a standard primitive used in the training of state-of-the-art image…
Existing saliency models have been designed and evaluated for predicting the saliency in distortion-free images. However, in practice, the image quality is affected by a host of factors at several stages of the image processing pipeline…
This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data…
Advances in machine learning have enabled the creation of realistic synthetic videos known as deepfakes. As deepfakes proliferate, concerns about rapid spread of disinformation and manipulation of public perception are mounting. Despite the…
The development of fair and ethical AI systems requires careful consideration of bias mitigation, an area often overlooked or ignored. In this study, we introduce a novel and efficient approach for addressing biases called Targeted Data…
Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by small perturbations to inputs that are often imperceivable…
Data augmentation is a critical component of training deep learning models. Although data augmentation has been shown to significantly improve image classification, its potential has not been thoroughly investigated for object detection.…
We introduce a set of image transformations that can be used as corruptions to evaluate the robustness of models as well as data augmentation mechanisms for training neural networks. The primary distinction of the proposed transformations…
Data augmentation is a major component of many machine learning methods with state-of-the-art performance. Common augmentation strategies work by drawing random samples from a space of transformations. Unfortunately, such sampling…
3D softwares are now capable of producing highly realistic images that look nearly indistinguishable from the real images. This raises the question: can real datasets be enhanced with 3D rendered data? We investigate this question. In this…
Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the…
Data augmentation forms the cornerstone of many modern machine learning training pipelines; yet, the mechanisms by which it works are not clearly understood. Much of the research on data augmentation (DA) has focused on improving existing…