Image classification with symbolic hints using limited resources.
PLoS One
; 19(5): e0301360, 2024.
Article
en En
| MEDLINE
| ID: mdl-38771772
ABSTRACT
Typical machine learning classification benchmark problems often ignore the full input data structures present in real-world classification problems. Here we aim to represent additional information as "hints" for classification. We show that under a specific realistic conditional independence assumption, the hint information can be included by late fusion. In two experiments involving image classification with hints taking the form of text metadata, we demonstrate the feasibility and performance of the fusion scheme. We fuse the output of pre-trained image classifiers with the output of pre-trained text models. We show that calibration of the pre-trained models is crucial for the performance of the fused model. We compare the performance of the fusion scheme with a mid-level fusion scheme based on support vector machines and find that these two methods tend to perform quite similarly, albeit the late fusion scheme has only negligible computational costs.
Texto completo:
1
Colección:
01-internacional
Banco de datos:
MEDLINE
Asunto principal:
Máquina de Vectores de Soporte
Límite:
Humans
Idioma:
En
Revista:
PLoS One
Asunto de la revista:
CIENCIA
/
MEDICINA
Año:
2024
Tipo del documento:
Article
País de afiliación:
Dinamarca