augmentations

Generation and evaluation of synthetic time series datasets (also, augmentations, visualizations, a collection of popular datasets) NeurIPS'24

Train Scene Graph Generation for Visual Genome and GQA in PyTorch >= 1.2 with improved zero and few-shot generalization [BMVC 2020, ICCV 2021]

Custom image data generator for TF Keras that supports the modern augmentation module albumentations

Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently generate a wide range of illumination variants of a single image.

⚡ Blazing fast audio augmentation in Python, powered by GPU for high-efficiency processing in machine learning and audio analysis tasks.

Repo for the paper "Extrapolating from a Single Image to a Thousand Classes using Distillation"

RuTransform: python framework for adversarial attacks and text data augmentation for Russian

This repo contains full solution for the challenge: from datasets creation to training and creating submit file. Moreover it can be used as a universal high-quality baseline solution for any segmentation task.

Official implementation for "Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images" https://arxiv.org/abs/2112.08810

Repository for the paper "Exploring Image Augmentations for Siamese Representation Learning with Chest X-Rays"

Runner Up Solution for the NeurIPS 2020 Competition - "Predicting Generalization in Deep Learning"

Source code of top 3% solution for the Kaggle APTOS 2019 Blindness Detection challenge.

Aug Tool is a Python library available on PyPI that simplifies image data augmentation for machine learning tasks, compatible with TensorFlow, PyTorch, and the YOLO library.

State-of-the-art https://arxiv.org/abs/2302.09119 https://intranet.matematicas.uady.mx/journal/index.php?c=50

Local web application providing API and UI for image augmentation, based on the albumentations library

Augmentation yolo format txt and images

VAE learned on augmented data to improve generalization.

Self-Supervised Contrastive Learning for light-weight models in EEG-based sleep stage classification

our objective is to create a reliable dataset by employing data augmentation algorithms. Using this improved GoEmotion dataset, we trained a transformer model with the ability to understand emotions from a given text.