Updated 6 months ago

boxsers • Rank 9.7 • Science 67%

Python package that provides a full range of functionality to process and analyze vibrational spectra (Raman, SERS, FTIR, etc.).

Updated 6 months ago

snorkel • Rank 23.6 • Science 46%

A system for quickly generating training data with weak supervision

Updated 6 months ago

pyraug • Rank 10.4 • Science 44%

Data Augmentation with Variational Autoencoders (TPAMI)

Updated 6 months ago

targetran • Rank 7.9 • Science 44%

Python library for data augmentation in object detection or image classification model training

Updated 5 months ago

https://github.com/albumentations-team/albucore • Rank 4.8 • Science 26%

A high-performance image processing library designed to optimize and extend the Albumentations library with specialized functions for advanced image transformations. Perfect for developers working in computer vision who require efficient and scalable image augmentation.

Updated 5 months ago

SpecAugment • Rank 8.5 • Science 10%

A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain

Updated 6 months ago

nfr • Science 54%

Neural Fuzzy Repair (NFR) is a data augmentation pipeline, which integrates fuzzy matches (i.e. similar translations) into neural machine translation.

Updated 6 months ago

aapi_code • Science 26%

A local application frontend and a backend server based on U-Net and Dectectron2 as a solution to the auto annotation of pathology images (Columbia Data Science Institute Fall 2020 Capstone Project)

Updated 5 months ago

https://github.com/amazon-science/transformers-data-augmentation • Science 26%

Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper

Updated 6 months ago

icsfsurvey • Science 54%

Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasoning elevation🍓 and hallucination alleviation🍄.

Updated 5 months ago

https://github.com/cgcl-codes/transferattacksurrogates • Science 13%

The official code of IEEE S&P 2024 paper "Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability". We study how to train surrogates model for boosting transfer attack.

Updated 5 months ago

https://github.com/aiot-mlsys-lab/deepaa • Science 26%

[ICLR 2022] "Deep AutoAugment" by Yu Zheng, Zhi Zhang, Shen Yan, Mi Zhang

Updated 6 months ago

p3forecast • Science 41%

a Personalized Privacy Preserving cloud workload prediction framework based on Federated Generative Adversarial Networks (GANs), which allows cloud providers with Non-IID workload data to collaboratively train workload prediction models as preferred while protecting privacy.

Updated 6 months ago

deeptrack • Science 67%

DeepTrack2 is a modular Python library for generating, manipulating, and analyzing image data pipelines for machine learning and experimental imaging.