DeepAI
Log In Sign Up

Harmonization and the Worst Scanner Syndrome

01/15/2021
by   Daniel Moyer, et al.
0

We show that for a wide class of harmonization/domain-invariance schemes several undesirable properties are unavoidable. If a predictive machine is made invariant to a set of domains, the accuracy of the output predictions (as measured by mutual information) is limited by the domain with the least amount of information to begin with. If a real label value is highly informative about the source domain, it cannot be accurately predicted by an invariant predictor. These results are simple and intuitive, but we believe that it is beneficial to state them for medical imaging harmonization.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/05/2021

Causally Invariant Predictor with Shift-Robustness

This paper proposes an invariant causal predictor that is robust to dist...
06/11/2021

Invariant Information Bottleneck for Domain Generalization

The main challenge for domain generalization (DG) is to overcome the pot...
07/25/2022

Domain-invariant Feature Exploration for Domain Generalization

Deep learning has achieved great success in the past few years. However,...
03/21/2022

Domain Generalization by Mutual-Information Regularization with Pre-trained Models

Domain generalization (DG) aims to learn a generalized model to an unsee...
12/22/2020

Semi-Supervised Disentangled Framework for Transferable Named Entity Recognition

Named entity recognition (NER) for identifying proper nouns in unstructu...
09/06/2021

Optimal Prediction of Unmeasured Output from Measurable Outputs In LTI Systems

In this short article, we showcase the derivation of an optimal predicto...
06/09/2021

Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization

Domain shifts in the training data are common in practical applications ...