We use a contrastive self-supervised learning framework to estimate distancesto galaxies from their photometric images . We incorporate data augmentationsfrom computer vision as well as an application-specific augmentation accountingfor galactic dust . We find that the resulting visual representations of galaxyimages are semantically useful and allow for fast similarity searches, and can be successfully fine-tuned for the task of redshift estimation . We show that pretraining on a large corpus of unlabeled data followed by fine tuning onsome labels can attain the accuracy of a fully-supervisory model which requires2-4x more labeled data .
Author(s) : Md Abul Hayat, Peter Harrington, George Stein, Zarija Lukić, Mustafa MustafaLinks : PDF - Abstract
Code :
Keywords : data - supervised - learning - images - fine -
- Google Cloud Professional Data Engineer Specialization
- Deeplearning.ai Specialization by Andrew Ng
- Mathematics for Machine Learning by Marc Peter Deisenroth, A. Aldo Faisal and Cheng Soon Ong
- Learning How to Learn on Coursera
- Deep Learning A-Z
- Khan Academy Statistics and Probability
- The Hundred-Page Machine Learning Book
- Neural Networks from Scratch with Python by Sentdex