Towards Retrieval-Augmented Architectures for Image Captioning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sarto, Sara, Cornia, Marcella, Baraldi, Lorenzo, Nicolosi, Alessandro, Cucchiara, Rita
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913358465204224
author Sarto, Sara
Cornia, Marcella
Baraldi, Lorenzo
Nicolosi, Alessandro
Cucchiara, Rita
author_facet Sarto, Sara
Cornia, Marcella
Baraldi, Lorenzo
Nicolosi, Alessandro
Cucchiara, Rita
contents The objective of image captioning models is to bridge the gap between the visual and linguistic modalities by generating natural language descriptions that accurately reflect the content of input images. In recent years, researchers have leveraged deep learning-based models and made advances in the extraction of visual features and the design of multimodal connections to tackle this task. This work presents a novel approach towards developing image captioning models that utilize an external kNN memory to improve the generation process. Specifically, we propose two model variants that incorporate a knowledge retriever component that is based on visual similarities, a differentiable encoder to represent input images, and a kNN-augmented language model to predict tokens based on contextual cues and text retrieved from the external memory. We experimentally validate our approach on COCO and nocaps datasets and demonstrate that incorporating an explicit external memory can significantly enhance the quality of captions, especially with a larger retrieval corpus. This work provides valuable insights into retrieval-augmented captioning models and opens up new avenues for improving image captioning at a larger scale.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13127
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Retrieval-Augmented Architectures for Image Captioning
Sarto, Sara
Cornia, Marcella
Baraldi, Lorenzo
Nicolosi, Alessandro
Cucchiara, Rita
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Multimedia
The objective of image captioning models is to bridge the gap between the visual and linguistic modalities by generating natural language descriptions that accurately reflect the content of input images. In recent years, researchers have leveraged deep learning-based models and made advances in the extraction of visual features and the design of multimodal connections to tackle this task. This work presents a novel approach towards developing image captioning models that utilize an external kNN memory to improve the generation process. Specifically, we propose two model variants that incorporate a knowledge retriever component that is based on visual similarities, a differentiable encoder to represent input images, and a kNN-augmented language model to predict tokens based on contextual cues and text retrieved from the external memory. We experimentally validate our approach on COCO and nocaps datasets and demonstrate that incorporating an explicit external memory can significantly enhance the quality of captions, especially with a larger retrieval corpus. This work provides valuable insights into retrieval-augmented captioning models and opens up new avenues for improving image captioning at a larger scale.
title Towards Retrieval-Augmented Architectures for Image Captioning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Multimedia
url https://arxiv.org/abs/2405.13127