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 → dddzg → MoCo

dddzg / MoCo

Licence: MIT License
A pytorch reimplement of paper "Momentum Contrast for Unsupervised Visual Representation Learning"

Programming Languages

python
139335 projects - #7 most used programming language

Labels

papermocopytorch-reimplementmomentum-contrast

Projects that are alternatives of or similar to MoCo

Wavelet-like-Auto-Encoder
No description or website provided.
Stars: ✭ 61 (+48.78%)
Mutual labels:  paper
Movecraft
The original movement plugin for Bukkit. Reloaded. Again.
Stars: ✭ 79 (+92.68%)
Mutual labels:  paper
fake-news-detection
This repo is a collection of AWESOME things about fake news detection, including papers, code, etc.
Stars: ✭ 34 (-17.07%)
Mutual labels:  paper
OneStopEnglishCorpus
No description or website provided.
Stars: ✭ 38 (-7.32%)
Mutual labels:  paper
DRL in CV Papers
Research publications in Computer Vision Journals and Conferences (and arxiv) using RL.Visit Website:
Stars: ✭ 31 (-24.39%)
Mutual labels:  paper
Lottery Ticket Hypothesis-TensorFlow 2
Implementing "The Lottery Ticket Hypothesis" paper by "Jonathan Frankle, Michael Carbin"
Stars: ✭ 28 (-31.71%)
Mutual labels:  paper
paper-synthesizing-benchmarks
📝 "Synthesizing Benchmarks for Predictive Modeling" (🥇 CGO'17 Best Paper)
Stars: ✭ 21 (-48.78%)
Mutual labels:  paper
Restoring-Extremely-Dark-Images-In-Real-Time
The project is the official implementation of our CVPR 2021 paper, "Restoring Extremely Dark Images in Real Time"
Stars: ✭ 79 (+92.68%)
Mutual labels:  paper
Facial-Recognition-Attendance-System
An attendance system which uses facial recognition to detect which people are present in any image.
Stars: ✭ 48 (+17.07%)
Mutual labels:  paper
maml-rl-tf2
Implementation of Model-Agnostic Meta-Learning (MAML) applied on Reinforcement Learning problems in TensorFlow 2.
Stars: ✭ 16 (-60.98%)
Mutual labels:  paper
time series clustering via community detection
Code used in the paper "Time Series Clustering via Community Detection in Networks"
Stars: ✭ 27 (-34.15%)
Mutual labels:  paper
paper-template
Collection of paper latex template for several computer vision related conference.
Stars: ✭ 63 (+53.66%)
Mutual labels:  paper
Hyperverse
A Minecraft world management plugin
Stars: ✭ 53 (+29.27%)
Mutual labels:  paper
sensim
Sentence Similarity Estimator (SenSim)
Stars: ✭ 15 (-63.41%)
Mutual labels:  paper
CHyVAE
Code for our paper -- Hyperprior Induced Unsupervised Disentanglement of Latent Representations (AAAI 2019)
Stars: ✭ 18 (-56.1%)
Mutual labels:  paper
my-bookshelf
Collection of books/papers that I've read/I'm going to read/I would remember that they exist/It is unlikely that I'll read/I'll never read.
Stars: ✭ 49 (+19.51%)
Mutual labels:  paper
Islands
A spigot plugin for creating customisable home islands with different biomes. https://www.spigotmc.org/resources/islands-home-islands-system.84303/
Stars: ✭ 18 (-56.1%)
Mutual labels:  paper
ocbnn-public
General purpose library for BNNs, and implementation of OC-BNNs in our 2020 NeurIPS paper.
Stars: ✭ 31 (-24.39%)
Mutual labels:  paper
paperback
Paper backup generator suitable for long-term storage.
Stars: ✭ 517 (+1160.98%)
Mutual labels:  paper
TMNet
The official pytorch implemention of the CVPR paper "Temporal Modulation Network for Controllable Space-Time Video Super-Resolution".
Stars: ✭ 77 (+87.8%)
Mutual labels:  paper
View All Similar Projects ➔

MoCo

A pytorch reimplement of paper "Momentum Contrast for Unsupervised Visual Representation Learning"

Shuffle BN can be applied although there is only one gpu.

Visualization

we randomly select an image (in the first row), and then find the most similar/dissimilar images with the largest/smallest dot product (in the second row and third row).

As seen, with unsupervised learning, the model can capture the similarity between images.

case 1

case 2

case 3

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].