contrastive-reconstruction
Tensorflow-keras implementation for Contrastive Reconstruction (ConRec) : a self-supervised learning algorithm that obtains image representations by jointly optimizing a contrastive and a self-reconstruction loss. (by bayer-science-for-a-better-life)
vissl
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images. (by facebookresearch)
| contrastive-reconstruction | vissl | |
|---|---|---|
| 1 | 2 | |
| 13 | 3,214 | |
| - | - | |
| 10.0 | 5.9 | |
| almost 3 years ago | 9 months ago | |
| Python | Jupyter Notebook | |
| GNU General Public License v3.0 only | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
contrastive-reconstruction
Posts with mentions or reviews of contrastive-reconstruction.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-10-15.
-
[D]Use SimCLR as pretraining for image segmentation
How about this: https://github.com/bayer-science-for-a-better-life/contrastive-reconstruction
vissl
Posts with mentions or reviews of vissl.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-10-15.
-
[D]Use SimCLR as pretraining for image segmentation
I recently did some self supervised pretrainings (simclr, moco, Barlow twins) and used the vissl library for that which has worked pretty well for me (https://github.com/facebookresearch/vissl)
-
[D] Paper Explained – SEER explained: Vision Models more Robust & Fair when pretrained on UNCURATED images!?
Official implementation: https://github.com/facebookresearch/vissl/tree/main/projects/SEER
What are some alternatives?
When comparing contrastive-reconstruction and vissl you can also consider the following projects:
MAGIST-Algorithm - Multi-Agent Generally Intelligent Simultaneous Training Algorithm for Project Zeta
solo-learn - solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
Unsupervised-Classification - SCAN: Learning to Classify Images without Labels, incl. SimCLR. [ECCV 2020]
self_supervised - Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.
mmselfsup - OpenMMLab Self-Supervised Learning Toolbox and Benchmark