paper

Labelled data is expensive, which makes benefiting from the current success in supervised learning unfeasible for smaller companies.

However, good representations can be learned without any task-specific information from raw data.

In self-supervised learning, labels are generated artificially. A common approach is to take multiple augmented views from the same source and contrast them to different sources.

Many papers have proven that simply increasing the similarity (decreasing the distance in the embedding space) of such views from the same source can lead to strong representations.

Srinivasan Keshav describes the three-pass approach which acts as a filtering system. It is an iterative and incremental way of reading a paper. It consists of: 

1. The First Pass: The bird's-eye view 
2. The second pass: Grasp the content
3. The third pass: Virtually re-implement the paper