0% Complete
صفحه اصلی
/
سی و دومین کنفرانس بین المللی مهندسی برق
Enhancing SCGAN’s Disentangled Representation Learning with Contrastive SSIM Similarity Constraints
نویسندگان :
Iman Yazdanpanah
1
Ali Eslamian
2
1- دانشگاه صنعتی اصفهان
2- دانشگاه صنعتی اصفهان
کلمات کلیدی :
Generative Adversarial Nets،Unsupervised Learning،Disentangled Representation Learning،Contrastive Disentanglement،SSIM
چکیده :
SCGAN adds a similarity constraint between generated images and conditions as a regularization term on generative adversarial networks. Similarity constraint works as a tutor to instruct the generator network to comprehend the difference in representations based on conditions. We understand how SCGAN works on a deeper level. This understanding makes us realize that the similarity constraint functions like the contrastive loss function. Two major changes we applied to SCGAN to make a modified model are using SSIM to measure similarity between images and applying contrastive loss principles to the similarity constraint. The modified model performs better using FID and Factor metrics. On the MNIST and Fashion-MNIST datasets, the modified model achieves log-likelihood values of 234.8 and 332.6, respectively, surpassing SCGAN’s 232.5 and 324.2. The modified model exhibits improvements in FID, attaining values of 3.42 and 12.97 for MNIST and Fashion-MNIST, respectively, compared to SCGAN’s 4.11 and 14.63. In terms of disentanglement, the modified model shows clear advantages, achieving values of 0.89 and 0.91 for MNIST and Fashion-MNIST, respectively, compared to SCGAN’s 0.77 and 0.89. These improvements show that the modified model has effectively learned a more disentangled representation compared to SCGAN. The modified model also has better generalisability compared to other models.
لیست مقالات
لیست مقالات بایگانی شده
توسعه نرمافزار تخمین عملکرد خطوط انتقال در برابر پدیده صاعقه
سعید شیرمحمدی - رضا شریعتی نسب - کاظم علیشاهی - سامان قهقه زاده
Second-Order Mode Analysis of Spoof Surface Plasmon Waveguide
Mohammad Ali Khosrovani_Moghaddam - Amir Ahmad Shishegar
The effect of metal rods in a hybrid plasmonic-photonic crystal cavity design
Leila Hajshahvaladi - Hassan Kaatuzian - Mohammad Danaie - Amirhossein Abdollahi Nohiji
رمزنگاری نوین صدا با استفاده از نظریه آشوب و عملگرهای ژنتیک در سامانههای VOIP
علی خرمی - جعفر شرفخانی
Design of Optimal Iterative Learning Control AutoPilot for Landing Fixed-Wing Aircraft
Ali Raddanipour - Masoud Shafiee
یک روش تشخیص و تصحیح خطا برای بلوک های داده
سعیده صادقی - محسن راجی
Event Related Potentials Extraction using Low-rank Tensor Decomposition
Zahra SohrabiBonab - Mohammad Bagher Shamsollahi
Zero control effort approach to perturbed coupled orbit-attitude periodic solution at three-body problem: Earth-Mars system
Amirreza Kosari - Ehsan Abbasali - Majid Bakhtiari
Automotive radar target classification using micro-Doppler features
Amin Aghatabarroodbary - Mohammad Hassan Bastani - Fereidoon Behnia
Development of Iterative Learning Control Method Based on Markov Parameters for High-Order Discrete-Time Singular Systems
Meysam Azhdari - Tahereh Binazadeh - Ali Gholami
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.4