arXiv Analytics

Sign in

arXiv:2202.10492 [cs.CV]AbstractReferencesReviewsResources

CaMEL: Mean Teacher Learning for Image Captioning

Manuele Barraco, Matteo Stefanini, Marcella Cornia, Silvia Cascianelli, Lorenzo Baraldi, Rita Cucchiara

Published 2022-02-21Version 1

Describing images in natural language is a fundamental step towards the automatic modeling of connections between the visual and textual modalities. In this paper we present CaMEL, a novel Transformer-based architecture for image captioning. Our proposed approach leverages the interaction of two interconnected language models that learn from each other during the training phase. The interplay between the two language models follows a mean teacher learning paradigm with knowledge distillation. Experimentally, we assess the effectiveness of the proposed solution on the COCO dataset and in conjunction with different visual feature extractors. When comparing with existing proposals, we demonstrate that our model provides state-of-the-art caption quality with a significantly reduced number of parameters. According to the CIDEr metric, we obtain a new state of the art on COCO when training without using external data. The source code and trained models are publicly available at: https://github.com/aimagelab/camel.

Related articles: Most relevant | Search more
arXiv:1912.08226 [cs.CV] (Published 2019-12-17)
M$^2$: Meshed-Memory Transformer for Image Captioning
arXiv:1708.05271 [cs.CV] (Published 2017-08-17)
Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects
arXiv:1805.09137 [cs.CV] (Published 2018-05-13)
Image Captioning