Unsupervised-Classification
self-supervised
| Unsupervised-Classification | self-supervised | |
|---|---|---|
| 2 | 2 | |
| 1,366 | 125 | |
| - | - | |
| 1.4 | 0.0 | |
| over 1 year ago | almost 2 years ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | - |
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.
Unsupervised-Classification
-
Middle ground dataset between CIFAR and ImageNet [D]
The subsets we used are from here: https://github.com/wvangansbeke/Unsupervised-Classification/tree/master/data/imagenet_subsets
- Any reference or idea about how to train unsupervised CNN model ?
self-supervised
-
[P] solo-learn: a library of self-supervised methods for visual representation learning
W-MSE
-
[R] ICLR rejected the submission only for missing large-scale ImageNet experiments
https://github.com/htdt/self-supervised it includes our method, byol and contrastive. I tried to keep the code nice and clean.
What are some alternatives?
simclr - SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
dino - PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Unsupervised-Semantic-Segmentation - Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals. [ICCV 2021]
Revisiting-Contrastive-SSL - Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations. [NeurIPS 2021]
DiffCSE - Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"
PASS - The PASS dataset: pretrained models and how to get the data
SimMIM - This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".
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.
PaddleHelix - Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集
Transformer-SSL - This is an official implementation for "Self-Supervised Learning with Swin Transformers".
transferlearning - Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习