Can adversarial training learn image captioning ?
arXiv:1910.14609
Abstract
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.
Accepted to NeurIPS 2019 ViGiL workshop
References in corpus (8)
- Conditional Generative Adversarial Nets
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- Improved Training of Wasserstein GANs
- The relativistic discriminator: a key element missing from standard GAN
- Language Generation with Recurrent Generative Adversarial Networks without Pre-training
- On Accurate Evaluation of GANs for Language Generation