Learning to Select:A Fully Attentive Approach for Novel Object Captioning

Abstract

Image captioning models have lately shown impressive results when applied to standard datasets. Switching to real-life scenarios, however, constitutes a challenge due to the larger variety of visual concepts which are not covered in existing training sets. For this reason, novel object captioning (NOC) has recently emerged as a paradigm to test captioning models on objects which are unseen during the training phase. In this paper, we present a novel approach for NOC that learns to select the most relevant objects ofan image, regardless of their adherence to the training set, and to constrain the generative process of a language model accordingly. Our architecture is fully-attentive and end-to-end trainable, also when incorporating constraints. We perform experiments on the held-outCOCO dataset, where we demonstrate improvements over the state of the art, both in terms of adaptability to novel objects and caption quality.

@article{cagrandi2021learning,
  title={Learning to Select: A Fully Attentive Approach for Novel Object Captioning},
  author={Cagrandi, Marco and Cornia, Marcella and Stefanini, Matteo and Baraldi, Lorenzo and Cucchiara, Rita},
  journal={arXiv preprint arXiv:2106.01424},
  year={2021}
}

Matteo Stefanini

PhD in Artificial Intelligence | TEDx Organizer

I’m a (deep) learner who loves freedom. Working on Deep Learning, Genomics, Gene expression and Vision & Language. Driven to be useful for people.