Cargando…
Interpreting vision and language generative models with semantic visual priors
When applied to Image-to-text models, explainability methods have two challenges. First, they often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated sequence. This makes explanations expensive to compute and unable to comprehensively expla...
| Autores principales: | , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Frontiers Media S.A.
2023
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10561255/ https://www.ncbi.nlm.nih.gov/pubmed/37818428 http://dx.doi.org/10.3389/frai.2023.1220476 |