Related papers: Survey: Image Mixing and Deleting for Data Augment…
Neural models often exploit superficial features to achieve good performance, rather than deriving more general features. Overcoming this tendency is a central challenge in areas such as representation learning and ML fairness. Recent work…
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…
Self-supervised learning has become a popular approach in recent years for its ability to learn meaningful representations without the need for data annotation. This paper proposes a novel image augmentation technique, overlaying images,…
Modern data augmentation using a mixture-based technique can regularize the models from overfitting to the training data in various computer vision applications, but a proper data augmentation technique tailored for the part-based…
Deep neural networks can be effective means to automatically classify aerial images but is easy to overfit to the training data. It is critical for trained neural networks to be robust to variations that exist between training and test…
Data augmentation techniques play an important role in enhancing the performance of deep learning models. Despite their proven benefits in computer vision tasks, their application in the other domains remains limited. This paper proposes a…
Data augmentation has become an integral part of deep learning, as it is known to improve the generalization capabilities of neural networks. Since the most effective set of image transformations differs between tasks and domains, automatic…
Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.…
Data augmentation is a series of techniques that generate high-quality artificial data by manipulating existing data samples. By leveraging data augmentation techniques, AI models can achieve significantly improved applicability in tasks…
Neural networks have shown great abilities in estimating depth from a single image. However, the inferred depth maps are well below one-megapixel resolution and often lack fine-grained details, which limits their practicality. Our method…
Size of the training dataset is an important factor in the performance of a machine learning algorithms and tools used in medical image processing are not exceptions. Machine learning tools normally require a decent amount of training data…
We introduce Network Augmentation (NetAug), a new training method for improving the performance of tiny neural networks. Existing regularization techniques (e.g., data augmentation, dropout) have shown much success on large neural networks…
Deep neural networks often make decisions based on the spurious correlations inherent in the dataset, failing to generalize in an unbiased data distribution. Although previous approaches pre-define the type of dataset bias to prevent the…
Mixup~\cite{zhang2017mixup} is a recently proposed method for training deep neural networks where additional samples are generated during training by convexly combining random pairs of images and their associated labels. While simple to…
A problem with Convolutional Neural Networks (CNNs) is that they require large datasets to obtain adequate robustness; on small datasets, they are prone to overfitting. Many methods have been proposed to overcome this shortcoming with CNNs.…
The large capacity of neural networks enables them to learn complex functions. To avoid overfitting, networks however require a lot of training data that can be expensive and time-consuming to collect. A common practical approach to…
We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. During training, our…
Data augmentation is one of the most common tools in deep learning, underpinning many recent advances including tasks such as classification, detection, and semantic segmentation. The standard approach to data augmentation involves simple…
Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image…
While machine learning approaches to image restoration offer great promise, current methods risk training models fixated on performing well only for image corruption of a particular level of difficulty---such as a certain level of noise or…