Extending Contrastive Learning to the Supervised Setting

Posted by AJ Maschinot, Senior Software Engineer and Jenny Huang, Product Manager, Google Research In recent years, self-supervised representation learning, which is used in a variety of image and video tasks, has significantly advanced due to the application of contrastive learning. These contrastive learning approaches typically teach a model to pull together the representations of a target image (a.k.a., the “anchor”) and a matching (“positive”) image in embedding space, while also pushing ap...

Submit