文本挖掘和预处理工具（文本清洗、新词发现、情感分析、实体识别链接、关键词抽取、知识抽取、句法分析等），无监督或弱监督方法

(CVPR'20 Oral) Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild

Pytorch version of SfmLearner from Tinghui Zhou et al.

Machine learning movie recommending system

A Non-Autoregressive Transformer based Text-to-Speech, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate TTS

CVPR2018: Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatio-temporal Patterns

This project proposes an end-to-end framework for semi-supervised Anomaly Detection and Segmentation in images based on Deep Learning.

Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model

Official PyTorch implementation of SynDiff described in the paper (https://arxiv.org/abs/2207.08208).

DualGAN-tensorflow: tensorflow implementation of DualGAN

A high performance impermentation of Unsupervised Image Segmentation by Backpropagation - Asako Kanezaki

Official PyTorch code for WACV 2022 paper "CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows"

(ECCV 2022) Code for Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency

A Non-Autoregressive End-to-End Text-to-Speech (text-to-wav), supporting a family of SOTA unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate E2E-TTS

[ICCV 2021] Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation

This repository tries to provide unsupervised deep learning models with Pytorch

Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification. ECCV'20 (Oral)

[Arxiv2020] The code for our paper 《Self-Supervised Temporal-Discriminative Representation Learning for Video Action Recognition》 https://arxiv.org/abs/2008.02129

Analysis scripts for log data sets used in anomaly detection.

本项目实现了一种基于 VAE-CycleGAN 的图像重建无监督缺陷检测算法。该算法结合了变分自编码器 (VAE) 和 CycleGAN 的优势，无需标注数据即可检测图像中的缺陷/异常。This project implements an unsupervised defect detection algorithm for image reconstruction based on VAE-CycleGAN. This algorithm combines the advantages of variational autoencoders (VAE) and CycleGAN to detect defects in images without any supervision.