Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

DeepCMB: Saliency for Image-to-Image Regression [Poster]

Technical Report ·
DOI:https://doi.org/10.2172/1637621· OSTI ID:1637621
 [1];  [2];  [3]
  1. Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
  2. Univ. of Chicago, IL (United States). Kavli Inst. for Cosmological Physics (KICP)
  3. 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.
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