arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.12137cs.CV
收藏

使用BERT循环文本到图像GAN

Cycle Text-To-Image GAN with BERT

Computer Science Dept.(计算机科学系)

Trevor Tsue, Samir Sen, Jason Li

摘要:

我们探索新的方法来从各自的字幕生成图像的任务,建立在最先进的GAN架构。特别是,我们使用基于注意力的GANs为我们的模型建立基线,这些GANs学习从单词到图像特征的注意力映射。为了更好地捕捉描述的特征,我们构建了一个新颖的循环设计,该设计学习了一个反函数来将图像映射回原始标题。此外,我们将最近开发的BERT预训练词嵌入作为我们的初始文本特征化器,并观察到与Attention GAN基线相比,定性和定量性能有明显的改善。

英文摘要:

We explore novel approaches to the task of image generation from their respective captions, building on state-of-the-art GAN architectures. Particularly, we baseline our models with the Attention-based GANs that learn attention mappings from words to image features. To better capture the features of the descriptions, we then built a novel cyclic design that learns an inverse function to maps the image back to original caption. Additionally, we incorporated recently developed BERT pretrained word embeddings as our initial text featurizer and observe a noticeable improvement in qualitative and quantitative performance compared to the Attention GAN baseline.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑