Google Open Sources SimCLR, A Framework for Self-Supervised and Semi-Supervised Image Training

High quality labeled datasets remain one of the biggest obstacles for the mainstream adoption of machine learning technologies. While we are seeing unprecedented advancements in machine learning research and technology, many of those methods can't be widely adopted due to limitations in the creation of training datasets. That hurtle has propelled research in alternative methods such as semi-supervised and self-supervised learning which are able to operate by pretraining with unlabeled datasets. In the language analysis front, we have seen remarkable achievements of these type of techniques with models such as Google BERT or Microsoft Turin-NLG breaking records in performance and efficiency. Other deep learning domains remain behind in the adoption of semi-supervised and self-supervised models.