Derin öğrenme alanında yaşanan en önemli gelişmelerden biri, hiç şüphesiz çekişmeli üretken ağ (Generative adversarial network-GAN) modelleridir. GAN olarak anılan bu modeller, görüntü veri kümesinin genişletilmesinde (image augmentation), resim/karikatür boyamada (painting), yüksek çözünürlüğe sahip süper görüntü elde etmede, bir görüntüdeki doku/desenin başka bir görüntüye transferinde kullanılan en modern yaklaşımlar olarak karşımıza çıkmaktadır. Bu çalışmada literatürde yaygın olarak kullanılan GAN modellerinin (cGAN, DCGAN, InfoGAN, SGAN, ACGAN, WGAN-GP, LSGAN), gerçek görüntülere çok benzeyen sentetik görüntüleri üretmedeki performansları incelenmiştir. Çalışmanın orijinalliği, cGAN ve DCGAN’ın avantajlarını barındıran hibrit bir GAN modeli (cDCGAN) geliştirilmesi ve GAN yöntemlerinin performansları, derin öğrenme tabanlı evrişimsel sinir ağları(CNN) ile kıyaslamalı olarak değerlendirmesidir. Kodlanan modellerle veri kümelerindeki görüntülere benzer sentetik görüntüler üretilmiştir. Üretilen sentetik görüntülerin mevcut görüntülere benzerliklerini hesaplamak, böylece model performansını değerlendirebilmek için fréchet başlangıç mesafesi (FID) metriği ve CNN kullanılmıştır. Yapılan deneysel çalışmalarda, tüm modellerin zamana bağlı görüntü üretim performansları değerlendirilmiştir. Sonuç olarak, LSGAN modeliyle üretilen görüntülerin yüksek sınıflandırma başarım oranı sağladığı, ancak DCGAN ve WGANGP ile daha gürültüsüz net görüntüler ürettiği gözlemlenmiştir.
One of the most important developments in the field of deep learning is undoubtedly the controversial generative adversarial network-GAN models. These models, known as GAN, are the most modern approaches used in the extension of the image data set (image augmentation), painting of the image/cartoon, achieving a high-resolution super image, transferring the texture/design in one image to another image. This study has studied the performance of the GAN models (cGAN, DCGAN, InfoGAN, SGAN, ACGAN, WGAN-GP, LSGAN) widely used in literature in producing synthetic images very similar to real images. The originality of the study is the development of a hybrid GAN model (cDCGAN) which has the benefits of cGAN and DCGAN and the performance of GAN methods is comparable to deep learning-based evolutionary nerve networks (CNN). The coded models have produced synthetic images similar to the images in data sets. For the calculation of the similarities of the produced synthetic images to the existing images, so that the performance of the model is assessed, the fréchet starting distance (FID) metric and CNN have been used. In experimental studies, the time-related image production performance of all models has been assessed. As a result, it has been observed that images produced with the LSGAN model provide a high classification success rate, but with DCGAN and WGANGP produce more noise-free clear images.
One of the most important developments in the field of deep learning is the generative adversarial network(GAN) models. These models, known as GAN, are the most modern approaches used in image editing, image/cartoon painting, high resolution super image acquisition, and the transfer of the texture/pattern in another image to another image. In this study, the performances of GAN models (cGAN, DCGAN, InfoGAN, SGAN, ACGAN, WGAN-GP, LSGAN), which are commonly used in the literature, in producing synthetic images very similar to the real images were investigated. The originality of the study is the development of a hybrid GAN model (cDCGAN) that incorporates the advantages of cGAN and DCGAN and evaluates the performances of GAN methods in comparison with deep learning based convolutional neural networks (CNN). Synthetic images similar to the images in the data sets were generated with the encoded models. Fréchet inception distance (FID) metric and CNN were used to calculate the similarity of the produced synthetic images to the existing images so as to evaluate the model performance. In the experimental studies, time-based image production performances of all models were evaluated. As a result, it was observed that the images produced by the LSGAN model provide a high classification performance rate, but with DCGAN and WGANGP, it produces clearer noise images.
Alan : Eğitim Bilimleri; Fen Bilimleri ve Matematik; Mühendislik
Dergi Türü : Ulusal
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|