In this paper, we consider the image captioning task from a new sequence-to-sequence prediction perspective and propose CaPtion TransformeR (CPTR) which takes the sequentialized raw images as the input to Transformer. Compared to the "CNN+Transformer" design paradigm, our model can model global context at every encoder layer from the beginning and is totally convolution-free. Extensive experiments demonstrate the effectiveness of the proposed model and we surpass the conventional "CNN+Transformer" methods on the MSCOCO dataset. Besides, we provide detailed visualizations of the self-attention between patches in the encoder and the "words-to-patches" attention in the decoder thanks to the full Transformer architecture.
@article{arxiv.2101.10804,
title = {CPTR: Full Transformer Network for Image Captioning},
author = {Wei Liu and Sihan Chen and Longteng Guo and Xinxin Zhu and Jing Liu},
journal= {arXiv preprint arXiv:2101.10804},
year = {2021}
}