auto-encoder

Reference code for the paper: Deep White-Balance Editing (CVPR 2020). Our method is a deep learning multi-task framework for white-balance editing.

The purpose of this repository is to make prototypes as case study in the context of proof of concept(PoC) and research and development(R&D) that I have written in my website. The main research topics are Auto-Encoders in relation to the representation learning, the statistical machine learning for energy-based models, adversarial generation networks(GANs), Deep Reinforcement Learning such as Deep Q-Networks, semi-supervised learning, and neural network language model for natural language processing.

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

Anomaly detection tutorial on univariate time series with an auto-encoder

Pytorch code for ICRA'22 paper: "Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation"

Experiments on unsupervised point cloud reconstruction.

CAE-LO: LiDAR Odometry Leveraging Fully Unsupervised Convolutional Auto-Encoder for Interest Point Detection and Feature Description

Tensorflow implementation of Semi-supervised Sequence Learning (https://arxiv.org/abs/1511.01432)

由时间空间成对组成的轨迹序列，通过循环神经网络lstm，自编码器auto-encode，时空密度聚类st-dbscan做异常检测

Face enhancer‏ - Denoising Auto Encoder by Tensorflow and Keras and skimage

Implementation of a 3D Face Generative Model

Drug Similarity Integration Through Attentive Multi-view Graph Auto-Encoders (IJCAI 2018)

Attention Deeplabv3+: Multi-level Context Attention Mechanism for Skin Lesion Segmentation

Custom PyTorch model (VGG-16 Auto-Encoder) and custom criterion (Local Aggregation) for image clustering. The repo contains elaborated creation of fungi image data using factory method.

Implementation of 'Self-Adversarial Variational Autoencoder with Gaussian Anomaly Prior Distribution for Anomaly Detection'

A system that will help in a personalized recommendation of courses for an upcoming semester based on the performance of previous semesters.

Learning Embedding of 3D models with Quadric Loss

The unsupervised learning problem trains a diffeomorphic spatio-temporal grid, that registers the output sequence of the PDEs onto a non-uniform parameter/time-varying grid, such that the Kolmogorov n-width of the mapped data on the learned grid is minimized.

Modern Deep Network Toolkits for Tensorflow-Keras. This is a extension for newest tensorflow 1.x.

A simple document and image search engine implemented in keras