papers AI Learner
The Github is limit! Click to go to the new site.

COMIC: Towards A Compact Image Captioning Model with Attention

2019-03-04
Jia Huei Tan, Chee Seng Chan, Joon Huang Chuah

Abstract

Recent works in image captioning have shown very promising raw performance. However, we realize that most of these encoder-decoder style networks with attention do not scale naturally to large vocabulary size, making them difficult to be deployed on embedded system with limited hardware resources. This is because the size of word and output embedding matrices grow proportionally with the size of vocabulary, adversely affecting the compactness of these networks. To address this limitation, this paper introduces a brand new idea in the domain of image captioning. That is, we tackle the problem of compactness of image captioning models which is hitherto unexplored. We showed that, our proposed model, named COMIC for COMpact Image Captioning, achieves comparable results in five common evaluation metrics with state-of-the-art approaches on both MS-COCO and InstaPIC-1.1M datasets despite having an embedding vocabulary size that is 39x - 99x smaller.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.01072

PDF

http://arxiv.org/pdf/1903.01072


Similar Posts

Comments