论文标题
轻巧的生成对抗网络，用于文本引导的图像操纵
Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation
论文作者
论文摘要
我们提出了一种新型的轻质生成对抗网络，以使用自然语言描述进行有效的图像操纵。为了实现这一目标，提出了一个新的单词级别歧视器，它为生成器提供了在文字级别的细粒度训练反馈，以促进训练一个具有少量参数的轻量级生成器，但仍可以正确地关注图像的特定视觉属性，然后不影响文本中未描述其他内容的其他内容。此外，由于与每个单词相关的明确训练信号，歧视器也可以简化以具有轻量级的结构。与最新技术相比，我们的方法的参数数量少得多，但仍具有竞争性的操纵性能。广泛的实验结果表明，我们的方法可以更好地解散不同的视觉属性，然后将它们正确映射到相应的语义单词，从而使用自然语言描述实现更准确的图像修改。
We propose a novel lightweight generative adversarial network for efficient image manipulation using natural language descriptions. To achieve this, a new word-level discriminator is proposed, which provides the generator with fine-grained training feedback at word-level, to facilitate training a lightweight generator that has a small number of parameters, but can still correctly focus on specific visual attributes of an image, and then edit them without affecting other contents that are not described in the text. Furthermore, thanks to the explicit training signal related to each word, the discriminator can also be simplified to have a lightweight structure. Compared with the state of the art, our method has a much smaller number of parameters, but still achieves a competitive manipulation performance. Extensive experimental results demonstrate that our method can better disentangle different visual attributes, then correctly map them to corresponding semantic words, and thus achieve a more accurate image modification using natural language descriptions.
