Can adversarial training learn image captioning ?

31 Oct 2019  ·  Jean-Benoit Delbrouck, Bastien Vanderplaetse, Stéphane Dupont ·

Recently, generative adversarial networks (GAN) have gathered a lot of interest. Their efficiency in generating unseen samples of high quality, especially images, has improved over the years. In the field of Natural Language Generation (NLG), the use of the adversarial setting to generate meaningful sentences has shown to be difficult for two reasons: the lack of existing architectures to produce realistic sentences and the lack of evaluation tools. In this paper, we propose an adversarial architecture related to the conditional GAN (cGAN) that generates sentences according to a given image (also called image captioning). This attempt is the first that uses no pre-training or reinforcement methods. We also explain why our experiment settings can be safely evaluated and interpreted for further works.

PDF Abstract


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.