Self-Supervised Representation Learning
What if we can get labels for free for unlabelled data and train unsupervised dataset in a supervised manner?
self-supervised-learning representation-learning generative-modeling object-recognition generative-adversarial-networks computer-vision tutorial article

Self-supervised learning opens up a huge opportunity for better utilizing unlabelled data, while learning in a supervised learning manner. This post covers many interesting ideas of self-supervised learning tasks on images, videos, and control problems.

What if we can get labels for free for unlabelled data and train unsupervised dataset in a supervised manner? We can achieve this by framing a supervised learning task in a special form to predict only a subset of information using the rest. In this way, all the information needed, both inputs and labels, has been provided. This is known as self-supervised learning.

Don't forget to tag @lilianweng in your comment, otherwise they may not be notified.

Authors
Aloha!
Share this project
Similar projects
Self-supervised representation learning on videos
Everything you need to know about video-based approaches on self-supervised learning
SimCLR - Contrastive Learning of Visual Representations
How to load pretrained/finetuned SimCLR models from hub modules for fine-tuning.
A Few Favorite Recipes in Computer Vision & Deep Learning
This blog post enlists a few of my favorite recipes in deep learning in the context of computer vision (as of August 2020).
Prototypical Contrastive Learning (PCL) for Unsupervised Learning
Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of the popular ...
Top collections