Image Captioning is a task that requires models to acquire a multi-modal understanding of the world and to express this understanding in natural language text. While the state-of-the-art for this task has rapidly improved in terms of n-gram metrics, these models tend to output the same generic captions for similar images. In this work, we address this limitation and train a model that generates more diverse and specific captions through an unsupervised training approach that incorporates a learning signal from an Image Retrieval model. We summarize previous results and improve the state-of-the-art on caption diversity and novelty. We make our source code publicly available online.
@article{arxiv.1812.08126,
title = {Generating Diverse and Meaningful Captions},
author = {Annika Lindh and Robert J. Ross and Abhijit Mahalunkar and Giancarlo Salton and John D. Kelleher},
journal= {arXiv preprint arXiv:1812.08126},
year = {2018}
}
Comments
Accepted for presentation at The 27th International Conference on Artificial Neural Networks (ICANN 2018)