Unsupervised-Classification
DiffCSE
| Unsupervised-Classification | DiffCSE | |
|---|---|---|
| 2 | 3 | |
| 1,366 | 290 | |
| - | - | |
| 1.4 | 0.0 | |
| over 1 year ago | about 2 years ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | MIT License |
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 ?
DiffCSE
-
[N] MIT/Meta AI released their new SOTA unsupervised sentence embedding model "DiffCSE"
Code for https://arxiv.org/abs/2204.10298 found: https://github.com/voidism/DiffCSE
What are some alternatives?
simclr - SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
Revisiting-Contrastive-SSL - Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations. [NeurIPS 2021]
self-supervised - Whitening for Self-Supervised Representation Learning | Official repository
PromCSE - Code for "Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning (EMNLP 2022)"
Unsupervised-Semantic-Segmentation - Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals. [ICCV 2021]
inltk - Natural Language Toolkit for Indic Languages aims to provide out of the box support for various NLP tasks that an application developer might need
SimMIM - This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".
SimCSE - [EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
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.
Transformer-SSL - This is an official implementation for "Self-Supervised Learning with Swin Transformers".
pytorch-metric-learning - The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.