Contrastive Clustering with SwAV
This video explains a new algorithm combining self-supervised contrastive learning with clustering to learn better representations. This is done by predicting clusters from image features, and is extremely close in performance to full supervised learning, constrained on the ResNet50 architecture. Thanks for watching! Please Subscribe!
Paper Links:
Facebook AI Blog Post on this Paper: https://ai.facebook.com/blog/high-performance-self-supervised-image-classification-with-contrastive-clustering/
Contrasting Cluster Assignments: https://arxiv.org/abs/2006.09882
Salesforce Blog Prototypical Contrastive Learning: https://blog.einstein.ai/prototypical-contrastive-learning-pushing-the-frontiers-of-unsupervised-learning/
Prototypical Contrastive Learning Paper: https://arxiv.org/pdf/2005.04966.pdf
Supervised Contrastive Learning: https://arxiv.org/pdf/2004.11362.pdf
SimCLR: https://arxiv.org/pdf/2002.05709.pdf
Bootstrap your own Latent: https://arxiv.org/pdf/2006.07733.pdf
CURL: https://arxiv.org/pdf/2004.04136.pdf
Видео Contrastive Clustering with SwAV канала Connor Shorten
Paper Links:
Facebook AI Blog Post on this Paper: https://ai.facebook.com/blog/high-performance-self-supervised-image-classification-with-contrastive-clustering/
Contrasting Cluster Assignments: https://arxiv.org/abs/2006.09882
Salesforce Blog Prototypical Contrastive Learning: https://blog.einstein.ai/prototypical-contrastive-learning-pushing-the-frontiers-of-unsupervised-learning/
Prototypical Contrastive Learning Paper: https://arxiv.org/pdf/2005.04966.pdf
Supervised Contrastive Learning: https://arxiv.org/pdf/2004.11362.pdf
SimCLR: https://arxiv.org/pdf/2002.05709.pdf
Bootstrap your own Latent: https://arxiv.org/pdf/2006.07733.pdf
CURL: https://arxiv.org/pdf/2004.04136.pdf
Видео Contrastive Clustering with SwAV канала Connor Shorten
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![BYOL: Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning (Paper Explained)](https://i.ytimg.com/vi/YPfUiOMYOEE/default.jpg)
![SWaV: Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (Mathilde Caron)](https://i.ytimg.com/vi/uqJ2hbDGHjY/default.jpg)
![Clustering with DBSCAN, Clearly Explained!!!](https://i.ytimg.com/vi/RDZUdRSDOok/default.jpg)
![Deep Clustering with Convolutional Autoencoders](https://i.ytimg.com/vi/fxUaJSfZMxk/default.jpg)
![Don't Stop Pretraining!](https://i.ytimg.com/vi/zNjiTcF3FZE/default.jpg)
![](https://i.ytimg.com/vi/hwnXbnm9Ucw/default.jpg)
![Supervised Contrastive Learning](https://i.ytimg.com/vi/MpdbFLXOOIw/default.jpg)
![Self-Supervised Learning of Image Features with SwAV (with author Mathilde Caron)](https://i.ytimg.com/vi/7QmsTleiRLs/default.jpg)
![Learning To Classify Images Without Labels (Paper Explained)](https://i.ytimg.com/vi/hQEnzdLkPj4/default.jpg)
![Clustering: K-means and Hierarchical](https://i.ytimg.com/vi/QXOkPvFM6NU/default.jpg)
![What were the biggest advances in computer vision in 2021? | Roboflow + OpenCV webinar](https://i.ytimg.com/vi/Dz875QDxSh4/default.jpg)
![PR-231: A Simple Framework for Contrastive Learning of Visual Representations](https://i.ytimg.com/vi/FWhM3juUM6s/default.jpg)
![SimCLR: A Simple Framework for Contrastive Learning of Visual Representations](https://i.ytimg.com/vi/wySLC4nszv8/default.jpg)
![Variational deep embedding An unsupervised and generative approach to clustering](https://i.ytimg.com/vi/o0fQXZ9ReLQ/default.jpg)
![Deep Clustering: A Deep Learning Approach for High-Dimensional Data Clustering](https://i.ytimg.com/vi/0m5GNDo-CFM/default.jpg)
![SimCLR Explained!](https://i.ytimg.com/vi/APki8LmdJwY/default.jpg)
![Momentum Contrastive Learning](https://i.ytimg.com/vi/LvHwBQF14zs/default.jpg)
![self-supervised learning & contrastive learning (1)](https://i.ytimg.com/vi/0IozTsIJFNY/default.jpg)
![1.4. Unsupervised Learning | Clustering and Association Algorithms in Machine Learning](https://i.ytimg.com/vi/d9qf0qPPhsc/default.jpg)
![Few Shot Learning - EXPLAINED!](https://i.ytimg.com/vi/VqPmrYFvKf8/default.jpg)