-
Data augmentation using learned transformations for one-shot medical image se...
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used CIFAR-10, CIFAR-100, ImageNet, CUB-200-2011, and Stanford Dogs datasets. -
SelectAugment
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used CIFAR-10, CIFAR-100, ImageNet, CUB-200-2011, and Stanford Dogs datasets. -
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
SpecAugment is a data augmentation method for automatic speech recognition, which masks the mel-spectrogram along the time and frequency axes. -
MIXSPEECH: DATA AUGMENTATION FOR LOW-RESOURCE AUTOMATIC SPEECH RECOGNITION
MixSpeech is a data augmentation method for automatic speech recognition, which trains an ASR model by taking a weighted combination of two different speech features as the... -
Dirty Cityscapes
A dataset of 10k images with artificially generated soiling patterns, used for training and testing the soiling detection model. -
Dirty WoodScape
A companion dataset to the WoodScape dataset, containing 10k images with artificially generated soiling patterns. -
Generating Photo-Realistic Training Data to Improve Face Recognition Accuracy
Face datasets are widely used in face recognition tasks, but they are often limited by their size and quality. This paper proposes a method for generating photo-realistic... -
Cap2Aug: Caption guided Image to Image data Augmentation
Visual recognition in a low-data regime is challenging and often prone to overfitting. To mitigate this issue, several data augmentation strategies have been proposed. However,... -
Direct Differentiable Augmentation Search
Data augmentation has been an indispensable tool to improve the performance of deep neural networks, however the augmentation can hardly transfer among different tasks and... -
Synthetic Data
The dataset used in the paper is a synthetic dataset for off-policy contextual bandits, with contexts x ∈ X, a finite set of actions A, and bounded real rewards r ∈ A → [0, 1]. -
TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Tran...
Mixup is a commonly adopted data augmentation technique for image classification. Recent advances in mixup methods primarily focus on mixing based on saliency. -
Vietoris-Rips
The Vietoris-Rips dataset is used to evaluate the performance of the simplicial complex mixup method. -
SC-MAD: MIXTURES OF HIGHER-ORDER NETWORKS FOR DATA AUGMENTATION
The dataset used in the paper is a collection of simplicial complexes, which are higher-order networks that model complex interactions. -
Dataset for Image-to-Image Translation for Semantic Segmentation
The dataset used for the experiments with the proposed approach to augment image data for semantic segmentation networks by applying image-to-image translation with both, a... -
Mono-ViFI: A Unified Framework for Self-supervised Monocular Depth Estimation
Self-supervised monocular depth estimation has gathered no-table interest since it can liberate training from dependency on depth annotations. In monocular video training case,... -
SCD Datasets
A dataset containing 520 images from CPLC as the carton stacking skeleton datasets, and 269, 51, and 23 images from FM as the foreground texture datasets.
