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

Learning to Select


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.

ACM International Conference on Multimedia Retrieval - ICMR 2021

State of the art model for Novel Object Captioning on held-out COCO dataset.

Full Paper: pdf

Please cite with the following BibTeX:

  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},
Matteo Stefanini, PhD
Matteo Stefanini, PhD
Artificial Intelligence Project Manager | Innovation Manager | TEDx Organizer

I’m a connector, an innovation manager and a deep-learner who loves freedom and combining different ideas with science and entrepreneurship.