In this paper, we address the problem of image captioning specifically for molecular translation where the result would be a predicted chemical notation in InChI format for a given molecular structure. Current approaches mainly follow rule-based or CNN+RNN based methodology. However, they seem to underperform on noisy images and images with small number of distinguishable features. To overcome this, we propose an end-to-end transformer model. When compared to attention-based techniques, our proposed model outperforms on molecular datasets.
@article{arxiv.2104.14721,
title = {End-to-End Attention-based Image Captioning},
author = {Carola Sundaramoorthy and Lin Ziwen Kelvin and Mahak Sarin and Shubham Gupta},
journal= {arXiv preprint arXiv:2104.14721},
year = {2021}
}