کنفرانس مهندسی برق ایران

صفحه اصلی / بیست و نهمین کنفرانس مهندسی برق ایران

Multi wasserstien distance

نویسندگان :

Atefeh Ziaei Moghadam¹ Hamed Azarnoush² Seyyed Ali Seyyedsalehi³

1- دانشگاه امیرکبیر 2- دانشگاه امیرکبیر 3- دانشگاه امیرکبیر

کلمات کلیدی :

conditional generative adversarial network image-to-image translation, stain transfer, pathology

چکیده :

Conditional GANs (CGANs) use a condition to generate images. Adding a class condition to the discriminator helps improve the training process of GANs and has been widely used for CGAN. Therefore, many loss functions have been proposed for the discriminator to add class conditions to it. Many of them have the problem of adjusting weights. This paper presents a simple yet new loss function that uses class labels, but no adjusting is required. This loss function is based on WGAN-GP loss, and the discriminator has outputs of the same order (the reason for no adjusting). More specifically, the discriminator has K (the number of classes) outputs, and each of them is used to compute the distance between fake and real samples of one class. Another loss to enable the discriminator to classify is also proposed by applying softmax to the outputs and adding cross-entropy to our first loss. The proposed losses function is applied to a CGAN for image-to-image translation (here stain transformation for pathological images). The performances of proposed losses with some state-of-the-art losses are compared using Histogram Intersection Score between generated images using different loss functions and a reference image. The accuracy of a classifier is also computed to measure the quality of generated images. Our first loss performs almost similar to the loss that achieved the best results