Lemniscate.pytorchUnsupervised Feature Learning via Non-parametric Instance Discrimination
HidtOfficial repository for the paper "High-Resolution Daytime Translation Without Domain Labels" (CVPR2020, Oral)
AutovcAutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
Sc Sfmlearner ReleaseUnsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video (NeurIPS 2019)
PyodA Python Toolbox for Scalable Outlier Detection (Anomaly Detection)
Corex topicHierarchical unsupervised and semi-supervised topic models for sparse count data with CorEx
Enlightengan[IEEE TIP'2021] "EnlightenGAN: Deep Light Enhancement without Paired Supervision" by Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, Zhangyang Wang
Awesome VaesA curated list of awesome work on VAEs, disentanglement, representation learning, and generative models.
Disentangling VaeExperiments for understanding disentanglement in VAE latent representations
Recycle GanUnsupervised Video Retargeting (e.g. face to face, flower to flower, clouds and winds, sunrise and sunset)
CcCompetitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
PaseProblem Agnostic Speech Encoder
Mmt[ICLR-2020] Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification.
MlxtendA library of extension and helper modules for Python's data analysis and machine learning libraries.
DgiDeep Graph Infomax (https://arxiv.org/abs/1809.10341)
SelflowSelFlow: Self-Supervised Learning of Optical Flow
Chinese Ufldl Tutorial[UNMAINTAINED] 非监督特征学习与深度学习中文教程,该版本翻译自新版 UFLDL Tutorial 。建议新人们去学习斯坦福的CS231n课程,该门课程在网易云课堂上也有一个配有中文字幕的版本。
SimclrPyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations by T. Chen et al.
He4o和(he for objective-c) —— “信息熵减机系统”
SealionThe first machine learning framework that encourages learning ML concepts instead of memorizing class functions.
SpeechsplitUnsupervised Speech Decomposition Via Triple Information Bottleneck
CorexCorEx or "Correlation Explanation" discovers a hierarchy of informative latent factors. This reference implementation has been superseded by other versions below.
L2cLearning to Cluster. A deep clustering strategy.
TransferlearningTransfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
UEGAN[TIP2020] Pytorch implementation of "Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network"
adareg-monodispnetRepository for Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction (CVPR2019)
dti-clustering(NeurIPS 2020 oral) Code for "Deep Transformation-Invariant Clustering" paper
altairAssessing Source Code Semantic Similarity with Unsupervised Learning
back2futureUnsupervised Learning of Multi-Frame Optical Flow with Occlusions
MVGLTCyb 2018: Graph learning for multiview clustering
kwxBERT, LDA, and TFIDF based keyword extraction in Python
srVAEVAE with RealNVP prior and Super-Resolution VAE in PyTorch. Code release for https://arxiv.org/abs/2006.05218.
PiCIEPiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in clustering (CVPR2021)
PICParametric Instance Classification for Unsupervised Visual Feature Learning, NeurIPS 2020
kmedoidsThe Partitioning Around Medoids (PAM) implementation of the K-Medoids algorithm in Python [Unmaintained]
dti-sprites(ICCV 2021) Code for "Unsupervised Layered Image Decomposition into Object Prototypes" paper
Unsupervised-Learning-in-RWorkshop (6 hours): Clustering (Hdbscan, LCA, Hopach), dimension reduction (UMAP, GLRM), and anomaly detection (isolation forests).
deep learningDeep-learning approaches to object recognition from 3D data
uctfUnsupervised Controllable Text Generation (Applied to text Formalization)
treecutFind nodes in hierarchical clustering that are statistically significant
al-fk-self-supervisionOfficial PyTorch code for CVPR 2020 paper "Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision"
BaySMMModel for learning document embeddings along with their uncertainties
dadsCode for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.
KD3AHere is the official implementation of the model KD3A in paper "KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation".
NMFADMMA sparsity aware implementation of "Alternating Direction Method of Multipliers for Non-Negative Matrix Factorization with the Beta-Divergence" (ICASSP 2014).