unsupervised-machine-learning

Code for "Real-time self-adaptive deep stereo" - CVPR 2019 (ORAL)

Real-time GCC-NMF Blind Speech Separation and Enhancement

A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer (IJCAI 2019)

Stringlifier is on Opensource ML Library for detecting random strings in raw text. It can be used in sanitising logs, detecting accidentally exposed credentials and as a pre-processing step in unsupervised ML-based analysis of application text data.

Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification

Fast and explainable clustering in Python

TLDR is an unsupervised dimensionality reduction method that combines neighborhood embedding learning with the simplicity and effectiveness of recent self-supervised learning losses

✍️ An intelligent system that takes a document and classifies different writing styles within the document using stylometric techniques.

Repository For Codes And Concept Taught in Udemy Course

pyMCR: Multivariate Curve Resolution for Python

IAST: Instance Adaptive Self-training for Unsupervised Domain Adaptation (ECCV 2020) https://teacher.bupt.edu.cn/zhuchuang/en/index.htm

VAE with RealNVP prior and Super-Resolution VAE in PyTorch. Code release for https://arxiv.org/abs/2006.05218.

PyTorch implementation of 'An Unsupervised Neural Attention Model for Aspect Extraction' by He et al. ACL2017'

Hierarchical self-organizing maps for unsupervised pattern recognition

Invariant representation learning from imaging and spectral data

Unsupervised blind source separation of mixed images and sounds with variational auto-encoders.

A sparsity aware implementation of "Alternating Direction Method of Multipliers for Non-Negative Matrix Factorization with the Beta-Divergence" (ICASSP 2014).

TorchSOM is a PyTorch-based library for training Self-Organizing Maps (SOMs), a model trained in an unsupervised manner, that can be used for clustering, dimensionality reduction and data visualization. It is designed to be scalable and user-friendly.

HEAD-QA: A Healthcare Dataset for Complex Reasoning

Disentangling Motion, Foreground and Background Features in Videos