arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.14533cs.CV
收藏

DEff-GAN:用于Few-Shot图像合成的多种属性传递

DEff-GAN: Diverse Attribute Transfer for Few-Shot Image Synthesis

IIT Bombay(印度理工学院孟买分校)

Rajiv Kumar, G. Sivakumar

摘要:

大量数据的需求是训练许多GANs的难点。数据高效GANs涉及用有限的离散数据样本集拟合发电机连续目标分布,这是一项困难的任务。单图像方法集中于对单个图像的内部分布进行建模并生成其样本。虽然单图像方法可以合成具有多样性的图像样本,但它们不对多个图像进行建模或捕获两个图像之间可能的内在关系。我们只给出了少量的图像,我们感兴趣的是生成样本并利用输入图像中的共性。在这项工作中,我们扩展了单图像的GAN方法来模拟多个图像的样本合成。我们用一个辅助分类器分支修改了这个分类器,这有助于生成各种各样的样本并对输入标签进行分类。我们的数据高效GAN(DEff-GAN)在输入图像或类别之间可以绘制相似性和对应性时生成出色的结果。

英文摘要:

Requirements of large amounts of data is a difficulty in training many GANs. Data efficient GANs involve fitting a generators continuous target distribution with a limited discrete set of data samples, which is a difficult task. Single image methods have focused on modeling the internal distribution of a single image and generating its samples. While single image methods can synthesize image samples with diversity, they do not model multiple images or capture the inherent relationship possible between two images. Given only a handful of images, we are interested in generating samples and exploiting the commonalities in the input images. In this work, we extend the single-image GAN method to model multiple images for sample synthesis. We modify the discriminator with an auxiliary classifier branch, which helps to generate a wide variety of samples and to classify the input labels. Our Data-Efficient GAN (DEff-GAN) generates excellent results when similarities and correspondences can be drawn between the input images or classes.

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。

↑