Random-Erasing
Image augmentation library
Provides data augmentation techniques to enhance image classification models
Random Erasing Data Augmentation. Experiments on CIFAR10, CIFAR100 and Fashion-MNIST
723 stars
16 watching
156 forks
Language: Python
last commit: over 1 year ago aaai2020data-augmentationimage-classificationobject-detectionperson-re-identificationpytorch
Related projects:
Repository | Description | Stars |
---|---|---|
| An implementation of data augmentation techniques to improve the performance of saliency models on cluttered images | 11 |
| Provides a framework for learning with noisy labels using data augmentation strategies. | 113 |
| An investigation into the relationship between misleading images and hallucinations in large language models | 8 |
| This project controls vision-language models to restore degraded images in various environments and conditions. | 673 |
| An implementation of image dehazing and enhancement techniques in MATLAB | 119 |
| An implementation of a deep learning model for restoring images in various conditions | 817 |
| This software enables the creation of deep learning networks with stacked auto-encoders and fine-tunes them using backpropagation for image classification tasks. | 41 |
| Improving semantic segmentation robustness to motion blur using custom data augmentation techniques | 6 |
| Detects anomalies in hyperspectral images using an autoencoder-based approach | 45 |
| Reconstructs the internal state of a Mersenne Twister algorithm from partial output data | 71 |
| Library for audio data augmentation used in machine learning | 1,903 |
| Analyzing and mitigating object hallucination in large vision-language models to improve their accuracy and reliability. | 136 |
| This repository provides a PyTorch implementation of an image manipulation technique using a pretrained StyleGAN model. | 380 |
| A repository of statistical modeling materials and resources for an R course on Bayesian inference | 2,018 |
| Enhances image resolution while adding realistic details using AI-powered super-resolution techniques | 994 |