0% Complete
صفحه اصلی
/
بیست و نهمین کنفرانس مهندسی برق ایران
Multi wasserstien distance
نویسندگان :
Atefeh Ziaei Moghadam
1
Hamed Azarnoush
2
Seyyed Ali Seyyedsalehi
3
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
لیست مقالات
لیست مقالات بایگانی شده
Optimal Placement of Of Maintenance Teams in Distribution Networks to Minimize Energy Not Supplied
Qasem Asadi - Ali Ashoornezhad - Hamid Falaghi - Maryam Ramezani
Wideband Rat-race Hybrid Coupler Using Ridge Gap Waveguide Technology
Zahra Akhoondmahdi - Ahmad Bakhtafrouz
A Geometry-based Approach to Reduce the Quantization lobe in 1-bit Reconfigurable Intelligent Surfaces
Nima Ahmadi - Forouhar Farzaneh
Using a Novel Connection Triangle as a Classifier to Discriminate between Different Faults in the Frequency Response Analysis
Mohammad Hamed Samimi
A Low-profile Interdigital Diplexer for LEO Satellites Applications
Mojtaba Fallahzadeh - Behzad Ahmadi - Ali Kheirdoost
طراحی خودرمزگذار متغیر جهت تشخیص عیب در بیرینگهای غلتشی
مریم آهنگ - مهدی علیاری شورهدلی
بررسی و تحلیل تقابل تلفات و پروفیل ولتاژ به کمک الگوریتم ژنتیک چند هدفه در سیستم های قدرت در حضور سیستم های انتقال قدرت انعطاف پذیر
سجاد احمدنیا - حبیب رجبی مشهدی
Design and Implementation of a Data-Driven Controller for a Two-Wheeled Self-Balancing Robot
Mohammad Akhavan - Haniye Parvahan - Mojtaba Nouri Manzar
Electronic properties of 2D perovskites NMA2PbBr4 and NEA2PbBr4 for PeLED applications: first principle approach
Samad Shokouhi - Seyedeh bita Saadatmand - Vahid Ahmadi
یک روش مستقل از پارامترهای خطا بهمنظور تشخیص، دستهبندی و تعیین سکشن خطا در سیستم انتقال چند ترمیناله بر اساس تبدیل موجک گسسته
احسان اکبری - عبدالرضا شیخ الاسلامی
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 41.7.4