Cargando…
On the benefits of representation regularization in invariance based domain generalization
A crucial aspect of reliable machine learning is to design a deployable system for generalizing new related but unobserved environments. Domain generalization aims to alleviate such a prediction gap between the observed and unseen environments. Previous approaches commonly incorporated learning the...
Autores principales: | Shui, Changjian, Wang, Boyu, Gagné, Christian |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer US
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9012768/ https://www.ncbi.nlm.nih.gov/pubmed/35510180 http://dx.doi.org/10.1007/s10994-021-06080-w |
Ejemplares similares
-
Learning Invariant Representations using Mutual Information Regularization
por: Tan, Justin
Publicado: (2019) -
Learning Domain-Invariant Representations of Histological Images
por: Lafarge, Maxime W., et al.
Publicado: (2019) -
Automatic Seizure Classification Based on Domain-Invariant Deep Representation of EEG
por: Cao, Xincheng, et al.
Publicado: (2021) -
Symmetry, representations, and invariants
por: Goodman, Roe, et al.
Publicado: (2009) -
On the Invariant Regularization in Relativistic Quantum Theory
por: Pauli, W, et al.
Publicado: (1949)