GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → richzhang → Splitbrainauto

richzhang / Splitbrainauto

Licence: mit
Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction. In CVPR, 2017.

Programming Languages

shell
77523 projects

Labels

caffeunsupervised-learningautoencoder

Projects that are alternatives of or similar to Splitbrainauto

Pixelnet
The repository contains source code and models to use PixelNet architecture used for various pixel-level tasks. More details can be accessed at <http://www.cs.cmu.edu/~aayushb/pixelNet/>.
Stars: ✭ 194 (+41.61%)
Mutual labels:  caffe, unsupervised-learning
GuidedNet
Caffe implementation for "Guided Optical Flow Learning"
Stars: ✭ 28 (-79.56%)
Mutual labels:  caffe, unsupervised-learning
Hidden Two Stream
Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Stars: ✭ 179 (+30.66%)
Mutual labels:  caffe, unsupervised-learning
Danmf
A sparsity aware implementation of "Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection" (CIKM 2018).
Stars: ✭ 161 (+17.52%)
Mutual labels:  unsupervised-learning, autoencoder
Similarity-Adaptive-Deep-Hashing
Unsupervised Deep Hashing with Similarity-Adaptive and Discrete Optimization (TPAMI2018)
Stars: ✭ 18 (-86.86%)
Mutual labels:  caffe, unsupervised-learning
Tybalt
Training and evaluating a variational autoencoder for pan-cancer gene expression data
Stars: ✭ 126 (-8.03%)
Mutual labels:  unsupervised-learning, autoencoder
Change Detection Review
A review of change detection methods, including codes and open data sets for deep learning. From paper: change detection based on artificial intelligence: state-of-the-art and challenges.
Stars: ✭ 248 (+81.02%)
Mutual labels:  caffe, unsupervised-learning
Dual-CNN-Models-for-Unsupervised-Monocular-Depth-Estimation
Dual CNN Models for Unsupervised Monocular Depth Estimation
Stars: ✭ 36 (-73.72%)
Mutual labels:  autoencoder, unsupervised-learning
2D-and-3D-Deep-Autoencoder
Convolutional AutoEncoder application on MRI images
Stars: ✭ 57 (-58.39%)
Mutual labels:  autoencoder, unsupervised-learning
SESF-Fuse
SESF-Fuse: An Unsupervised Deep Model for Multi-Focus Image Fusion
Stars: ✭ 47 (-65.69%)
Mutual labels:  autoencoder, unsupervised-learning
Image similarity
PyTorch Blog Post On Image Similarity Search
Stars: ✭ 80 (-41.61%)
Mutual labels:  unsupervised-learning, autoencoder
Pyod
A Python Toolbox for Scalable Outlier Detection (Anomaly Detection)
Stars: ✭ 5,083 (+3610.22%)
Mutual labels:  unsupervised-learning, autoencoder
Calc
Convolutional Autoencoder for Loop Closure
Stars: ✭ 119 (-13.14%)
Mutual labels:  unsupervised-learning, autoencoder
Pt Dec
PyTorch implementation of DEC (Deep Embedding Clustering)
Stars: ✭ 132 (-3.65%)
Mutual labels:  autoencoder
Darknet2caffe
Convert darknet weights to caffemodel
Stars: ✭ 127 (-7.3%)
Mutual labels:  caffe
Gon
Gradient Origin Networks - a new type of generative model that is able to quickly learn a latent representation without an encoder
Stars: ✭ 126 (-8.03%)
Mutual labels:  unsupervised-learning
Autoregressive Predictive Coding
Autoregressive Predictive Coding: An unsupervised autoregressive model for speech representation learning
Stars: ✭ 138 (+0.73%)
Mutual labels:  unsupervised-learning
And
Official Pytorch Implementation for ICML'19 paper: Unsupervised Deep Learning by Neighbourhood Discovery
Stars: ✭ 133 (-2.92%)
Mutual labels:  unsupervised-learning
Srl Zoo
State Representation Learning (SRL) zoo with PyTorch - Part of S-RL Toolbox
Stars: ✭ 125 (-8.76%)
Mutual labels:  autoencoder
Seqface
SeqFace : Making full use of sequence information for face recognition
Stars: ✭ 125 (-8.76%)
Mutual labels:  caffe
View All Similar Projects ➔

Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction [Project Page]

Richard Zhang, Phillip Isola, Alexei A. Efros. In CVPR, 2017. (hosted on ArXiv)

Overview

This repository contains a pre-trained Split-Brain Autoencoder network. The network achieves state-of-the-art results on several large-scale unsupervised representation learning benchmarks.

Clone this repository

Clone the master branch of the respository using git clone -b master --single-branch https://github.com/richzhang/splitbrainauto.git

Dependencies

This code requires a working installation of Caffe. For guidelines and help with installation of Caffe, consult the installation guide and Caffe users group.

Test-Time Usage

(1) Run ./resources/fetch_models.sh. This will load model model_splitbrainauto_clcl.caffemodel. It will also load model model_splitbrainauto_clcl_rs.caffemodel, which is the model with the rescaling method from Krähenbühl et al. ICLR 2016 applied. The rescaling method has been shown to improve fine-tuning performance in some models, and we use it for the PASCAL tests in Table 4 in the paper. Alternatively, download the models from here and put them in the models directory.

(2) To extract features, you can (a) use the main branch of Caffe and do color conversion outside of the network or (b) download and install a modified Caffe and not worry about color conversion.

(a) Color conversion outside of prototxt To extract features with the main branch of Caffe:
(i) Load the downloaded weights with model definition file deploy_lab.prototxt in the models directory. The input is blob data_lab, which is an image in Lab colorspace. You will have to do the Lab color conversion pre-processing outside of the network.

(b) Color conversion in prototxt You can also extract features with in-prototxt color version with a modified Caffe.
(i) Run ./resources/fetch_caffe.sh. This will load a modified Caffe into directory ./caffe-colorization.
(ii) Install the modified Caffe. For guidelines and help with installation of Caffe, consult the installation guide and Caffe users group.
(iii) Load the downloaded weights with model definition file deploy.prototxt in the models directory. The input is blob data, which is a non mean-centered BGR image.

Citation

If you find this model useful for your resesarch, please use this bibtex to cite.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].