DeepCMB: Saliency for Image-to-Image Regression [Poster]
- Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
- Univ. of Chicago, IL (United States). Kavli Inst. for Cosmological Physics (KICP)
- Univ. of Chicago, IL (United States)
Saliency is an important technique for machine learning interpretability, often used in classification tasks. In this work we show how saliency can be used in an image-to-image regression task, aiding in the examination of the physics learned by the machine learning model.
- Research Organization:
- Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), High Energy Physics (HEP)
- DOE Contract Number:
- AC02-07CH11359
- OSTI ID:
- 1637621
- Report Number(s):
- FERMILAB-POSTER--19-128-AE-SCD; oai:inspirehep.net:1802296
- Country of Publication:
- United States
- Language:
- English
Similar Records
Multi-scale saliency search in image analysis.
A Dynamic Reduction Network for Point Clouds
Cognition at the Point of Sensing
Technical Report
·
Sat Oct 01 00:00:00 EDT 2005
·
OSTI ID:875629
A Dynamic Reduction Network for Point Clouds
Journal Article
·
Tue Mar 17 00:00:00 EDT 2020
· TBD
·
OSTI ID:1616312
Cognition at the Point of Sensing
Technical Report
·
Tue Sep 29 00:00:00 EDT 2020
·
OSTI ID:1668459