Viet-Anh on Software Logo

What is: PIRL?

SourceSelf-Supervised Learning of Pretext-Invariant Representations
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Pretext-Invariant Representation Learning (PIRL, pronounced as “pearl”) learns invariant representations based on pretext tasks. PIRL is used with a commonly used pretext task that involves solving jigsaw puzzles. Specifically, PIRL constructs image representations that are similar to the representation of transformed versions of the same image and different from the representations of other images.