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