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

Turbo Learning for Captionbot and Drawingbot

2018-11-29
Qiuyuan Huang, Pengchuan Zhang, Dapeng Wu, Lei Zhang

Abstract

We study in this paper the problems of both image captioning and text-to-image generation, and present a novel turbo learning approach to jointly training an image-to-text generator (a.k.a. CaptionBot) and a text-to-image generator (a.k.a. DrawingBot). The key idea behind the joint training is that image-to-text generation and text-to-image generation as dual problems can form a closed loop to provide informative feedback to each other. Based on such feedback, we introduce a new loss metric by comparing the original input with the output produced by the closed loop. In addition to the old loss metrics used in CaptionBot and DrawingBot, this extra loss metric makes the jointly trained CaptionBot and DrawingBot better than the separately trained CaptionBot and DrawingBot. Furthermore, the turbo-learning approach enables semi-supervised learning since the closed loop can provide pseudo-labels for unlabeled samples. Experimental results on the COCO dataset demonstrate that the proposed turbo learning can significantly improve the performance of both CaptionBot and DrawingBot by a large margin.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1805.08170

PDF

https://arxiv.org/pdf/1805.08170


Similar Posts

Comments