Predefined Prototypes for Intra-Class Separation and Disentanglement
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929397076852736 |
|---|---|
| author | Almudévar, Antonio Mariotte, Théo Ortega, Alfonso Tahon, Marie Vicente, Luis Miguel, Antonio Lleida, Eduardo |
| author_facet | Almudévar, Antonio Mariotte, Théo Ortega, Alfonso Tahon, Marie Vicente, Luis Miguel, Antonio Lleida, Eduardo |
| contents | Prototypical Learning is based on the idea that there is a point (which we call prototype) around which the embeddings of a class are clustered. It has shown promising results in scenarios with little labeled data or to design explainable models. Typically, prototypes are either defined as the average of the embeddings of a class or are designed to be trainable. In this work, we propose to predefine prototypes following human-specified criteria, which simplify the training pipeline and brings different advantages. Specifically, in this work we explore two of these advantages: increasing the inter-class separability of embeddings and disentangling embeddings with respect to different variance factors, which can translate into the possibility of having explainable predictions. Finally, we propose different experiments that help to understand our proposal and demonstrate empirically the mentioned advantages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_16145 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Predefined Prototypes for Intra-Class Separation and Disentanglement Almudévar, Antonio Mariotte, Théo Ortega, Alfonso Tahon, Marie Vicente, Luis Miguel, Antonio Lleida, Eduardo Machine Learning Artificial Intelligence Prototypical Learning is based on the idea that there is a point (which we call prototype) around which the embeddings of a class are clustered. It has shown promising results in scenarios with little labeled data or to design explainable models. Typically, prototypes are either defined as the average of the embeddings of a class or are designed to be trainable. In this work, we propose to predefine prototypes following human-specified criteria, which simplify the training pipeline and brings different advantages. Specifically, in this work we explore two of these advantages: increasing the inter-class separability of embeddings and disentangling embeddings with respect to different variance factors, which can translate into the possibility of having explainable predictions. Finally, we propose different experiments that help to understand our proposal and demonstrate empirically the mentioned advantages. |
| title | Predefined Prototypes for Intra-Class Separation and Disentanglement |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2406.16145 |