A New Perspective on Precision and Recall for Generative Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917507062824960 |
|---|---|
| author | Sykes, Benjamin Simon, Loïc Rabin, Julien Fadili, Jalal |
| author_facet | Sykes, Benjamin Simon, Loïc Rabin, Julien Fadili, Jalal |
| contents | With the recent success of generative models in image and text, the question of their evaluation has recently gained a lot of attention. While most methods from the state of the art rely on scalar metrics, the introduction of Precision and Recall (PR) for generative model has opened up a new avenue of research. The associated PR curve allows for a richer analysis, but their estimation poses several challenges. In this paper, we present a new framework for estimating entire PR curves based on a binary classification standpoint. We conduct a thorough statistical analysis of the proposed estimates. As a byproduct, we obtain a minimax upper bound on the PR estimation risk. We also show that our framework extends several landmark PR metrics of the literature which by design are restrained to the extreme values of the curve. Finally, we study the different behaviors of the curves obtained experimentally in various settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02414 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A New Perspective on Precision and Recall for Generative Models Sykes, Benjamin Simon, Loïc Rabin, Julien Fadili, Jalal Artificial Intelligence With the recent success of generative models in image and text, the question of their evaluation has recently gained a lot of attention. While most methods from the state of the art rely on scalar metrics, the introduction of Precision and Recall (PR) for generative model has opened up a new avenue of research. The associated PR curve allows for a richer analysis, but their estimation poses several challenges. In this paper, we present a new framework for estimating entire PR curves based on a binary classification standpoint. We conduct a thorough statistical analysis of the proposed estimates. As a byproduct, we obtain a minimax upper bound on the PR estimation risk. We also show that our framework extends several landmark PR metrics of the literature which by design are restrained to the extreme values of the curve. Finally, we study the different behaviors of the curves obtained experimentally in various settings. |
| title | A New Perspective on Precision and Recall for Generative Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2511.02414 |