jason718 / awesome-self-supervised-learning Goto Github PK
View Code? Open in Web Editor NEWA curated list of awesome self-supervised methods
A curated list of awesome self-supervised methods
Cool list! May I suggest adding the following paper to the Timeseries section:
Deldari, Shohreh, Dimitris Spathis, Mohammad Malekzadeh, Fahim Kawsar, Flora D. Salim, and Akhil Mathur. "CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent Masking." In Proceedings of the 17th ACM International Conference on Web Search and Data Mining, pp. 152-160. 2024. https://arxiv.org/abs/2307.16847
Hi @jason718 . Could you maybe add this review paper on future video frame prediction? Many thanks!
Multi-task Self-Supervised Learning for Human Activity Detection.
https://dl.acm.org/citation.cfm?id=3328932 (Official Link), https://arxiv.org/pdf/1907.11879.pdf (PDF)
Aaqib Saeed, Tanir Ozcelebi, Johan Lukkien. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies.
Hi,
Thanks for maintaining this repository. Appreciate your efforts.
Please add our paper "Contrastive Semi-Supervised Learning for 2D Medical Image Segmentation" that provides a novel way
to learn powerful representations in Semi-Supervised Setting using Contrastive Learning for images.
arXiv: https://arxiv.org/abs/2106.06801
The paper is accepted at MICCAI 2021.
The PDF link of ''Representation Learning by Learning to Count'' is https://arxiv.org/abs/1708.06734. Please correct it.
Many thanks for your kind sharing! Would you please help us to share our CVPR 2024 paper about SSL? Thank you very much!
Paper title: VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis
Publication: CVPR 2024
Paper link: https://arxiv.org/abs/2402.17300
Code link: https://github.com/Luffy03/VoCo
We appreciate your effort on the maintenance of this awesome repository.
We would like to recommend our recent research works on contrastive learning, which achieve state-of-the-art performance on popular benchmarks.
The papers are listed as follows:
Inter-Instance Similarity Modeling for Contrastive Learning
Asymmetric Patch Sampling for Contrastive Learning
Both of them provides open source code and trained model weights at Github, which can be found at following links:
https://github.com/visresearch/patchmix
https://github.com/visresearch/aps
Thanks!
Hi, thanks for this great list of works, it's been very useful ! Would you be able to add links to codes for the following two papers please :) ?
help needed! please consider contributing.
This is a really helpful list for the self-supervised learning.
The survey paper 'Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey.' is accepted by TPAMI 2020. Can you help to update it? Thanks!
The IEEE link is: https://ieeexplore.ieee.org/abstract/document/9086055
It's a nice repo! Just wondering why you didn't include the work from the Yann LeCun's group (did you)? I thought the name "self-supervised-learning" came from his group...maybe I was wrong since I am new to self-supervised-learning...:)
should be:
https://arxiv.org/abs/1904.09117
thanks for effort :)
The Sound of Pixels.
https://eccv2018.org/openaccess/content_ECCV_2018/papers/Hang_Zhao_The_Sound_of_ECCV_2018_paper.pdf (Official Link), https://arxiv.org/pdf/1907.11879.pdf (PDF)
https://github.com/hangzhaomit/Sound-of-Pixels (CODE)
Zhao, Hang and Gan, Chuang and Rouditchenko, Andrew and Vondrick, Carl and McDermott, Josh and Torralba, Antonio.
Great collection. Two papers missed probably:
Joint Unsupervised Learning of Deep Representations and Image Clusters. CVPR 2016 (yes, I am one of the authors, :))
Unsupervised Deep Embedding for Clustering Analysis. ICML 2016
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.