Existing approaches have limited scalability and robustness in handling more than two domains, since different models should be built independently for every pair of image domains. To address this limitation, reseachers propose StarGAN, a novel and scalable approach that can perform image-to-image translations for multiple domains using only a single model. Such a unified model architecture of StarGAN allows simultaneous training of multiple datasets with different domains within a single network.

(在此论文出世之前,以前的网络 pixel2pixel gan(针对 pair images),cyclegan(针对 unpair images)等都只能实现两个特定领域(domain)的风格转换。要是想实现 k (>2)个 domain 的转换,就得为对应的转换关系单独建立模型,即 k(k−1)  个生成器!,费时费力!starGan 同时在多个不同 label 的数据集上训练一个 model 即可。)

our model takes in training data of multiple domains, and learns the mappings between all available domains using only one generator. The idea is simple. Instead of learning a fixed translation (e.g., black-to-blond hair), our model takes in as inputs both image and domain information, and learns to flexibly translate the input image into the corresponding domain. We use a label (e.g., binary or one-hot vector) to represent domain information. During training, we randomly generate a target domain label and train the model to flexibly translate an input image into the target domain. By doing so, we can control the domain label and translate the image into any desired domain at testing phase.

save image(作者们为每个 domain 都制作一个 label,类似 one-hot vector 那种感觉。并且在训练时随机生成 domain label,这样就能保证从多个不同数据集生成不同的 domain 的结果!p.s. 这不就是个多分类??)

Share this to:


邮箱地址不会被公开。 必填项已用*标注