Semi-Supervised Variational Autoencoders for Out-of-Distribution Generation.
Entropy (Basel)
; 25(12)2023 Dec 14.
Article
en En
| MEDLINE
| ID: mdl-38136539
ABSTRACT
Humans are able to quickly adapt to new situations, learn effectively with limited data, and create unique combinations of basic concepts. In contrast, generalizing out-of-distribution (OOD) data and achieving combinatorial generalizations are fundamental challenges for machine learning models. Moreover, obtaining high-quality labeled examples can be very time-consuming and expensive, particularly when specialized skills are required for labeling. To address these issues, we propose BtVAE, a method that utilizes conditional VAE models to achieve combinatorial generalization in certain scenarios and consequently to generate out-of-distribution (OOD) data in a semi-supervised manner. Unlike previous approaches that use new factors of variation during testing, our method uses only existing attributes from the training data but in ways that were not seen during training (e.g., small objects of a specific shape during training and large objects of the same shape during testing).
Texto completo:
1
Colección:
01-internacional
Banco de datos:
MEDLINE
Idioma:
En
Revista:
Entropy (Basel)
Año:
2023
Tipo del documento:
Article
País de afiliación:
Suiza