لطفا منتظر بمانید ...
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
Improving the Reliability of Multicore Embedded Systems through an Evolutionary-based Task Scheduling Approach
Athena Abdi - Hamid R Zarandi
A Technical-Managerial Framework for Determining Periodic Performance Indices and Operating Ranges of Power Grid Frequency
Hamed Delkhosh - Hossein Seifi - Sajjad Gholamnejad - Morteza Yousefian
Enhanced Forward Model for Photoacoustic Imaging with Speed of Sound Compensation
Amirreza Jodeiry - Zahra Kavehvash
Dual-Input Single-Output High Step-Up DC-DC Converter for Renewable Energy Applications
Farid Mohammadi - Amir Khorsandi
Validation of statistical models for direction of arrival, time of arrival and received power in a simple indoor Terahertz channel
Sina Sheybani - Amir ahmad Shishegar
طراحی و ساخت تقویت کننده توان اصلاح شده مقاومتی-راکتیوی باند گسترده کلاس B/J با گین بالا در توان خروجی پشتی و شرایط بایاس کلاس AB
سارا آقاجانی - محمود کمره ای - مرضیه چگینی
Stability Analysis of a New Switched SEIAR-Vac-Iso Epidemic Model for the COVID-19
Amir Hossein Amiri Mehra - Mohsen Shafieirad - Zohreh Abbasi - Iman Zamani
Experimental Demonstration of a Tunable Plasma Frequency Selective Surface Based on Electrically Driven Microdischarge Cells
Farhad Shahgoli - Mahsa Sedaghat - Shokrollah Karimian
Design an Intelligent Fault Detection System for Spring-Drive Operating Mechanism of SF6 High Voltage Circuit Breaker Using ADAMS
Milad Tahvilzadeh - Mehdi Aliyari Shooredeli - Ali asghar Razi Kazemi
طراحی بهینه ی آرایه ی تُنُک بی افزونگی با فاصله ی ناصحیح میان عناصر
سید محمد حسینی - محمود کریمی
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.7.2