论文标题
循环文本对图像gan with bert
Cycle Text-To-Image GAN with BERT
论文作者
论文摘要
我们以最先进的gan架构为基础，探索了从各自的标题中产生图像生成任务的新方法。特别是，我们使用基于注意力的gan的模型基线，这些剂量从单词到图像特征学习了注意力映射。为了更好地捕获描述的特征，我们构建了一种新颖的循环设计，该设计学习了一个逆功能以将图像映射回原始字幕。此外，我们将最近开发的BERT识别单词嵌入为我们的初始文本特征器，并观察到与GAN基线相比，定性和定量性能的明显改善。
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.
