Federated Self-supervised Learning for Video Understanding — mentioned by niclane7

Wed, 22 Mar 2023 14:09:21 GMT

Regarding federated labeling, you might be interested in some recent prototypes built on Flower that use forms of self supervised learning. By combining SSL with federated learning we can start to leverage unlabeled data and this will be a big deal once it becomes common place. I'd suggest looking at these two research papers that build on Flower and include members of the Flower team as authors: https://arxiv.org/abs/2207.01975 https://arxiv.org/abs/2204.02804

Paper and discussion history. A mention is not an endorsement.

Federated Self-supervised Learning for Video Understanding · HackerPapers discussions

Federated Self-supervised Learning for Video Understanding — mentioned by niclane7