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
Fusion of Multi-Level CNN With LBP Features For Facial Emotion Recognition
Ehsan Bahmanabady - Maryam Imani - Hassan Ghassemian
Impact of Sierpinski fractal shape on the performance of ultrathin-film silicon solar cells
Mohammad Ali Shameli - Sayyed Reza Mirnaziry - Leila Yousefi
بررسی تاثیر اعمال پوشش مش متال در مقاومت حرارتی و خوردگی سیم فولادی استحکام بالا بعنوان مغزی هادی های پرظرفیت ACSS
فائزه راد - مهرنوش طاهرخانی - ناصر میرشاه ولایتی - عبداله جواهری
Direct model reference adaptive control for depth of hypnosis in anesthesia
Raha Rahimi - Farzaneh Shayegh - Marzieh Kamali
ساخت حسگر رطوبت مقاومتی با استفاده از نانوذره اکسید گرافن بر پایه الکترودهای شانه ای
ندا قربانی - سمانه حامدی
طراحی یک کنترلکننده غیرخطی تطبیقی غیرمتمرکز برای تنظیم ولتاژ ریزشبکههای DC در حالت جزیرهای
سمیه بهرامی - فاطمه صفایی
Non-Invasive Blood Pressure Estimation using Poincaré Plot Indices of Photoplethysmography Signals
Fatemeh Shoeibi - Esmaeil Najafiaghdam - Afshin Ebrahimi
Applying Parameter-Oriented Learning to Identify Statistical EEG Features Associated with Depression
Sara Bargi Barkouk - Melika Changizi - Mahdi Zolfagharzadeh Kermani - Ali Asadi Zeidabadi
Holographic Principle Inspired Metal-Only Spoof Surface Plasmon Polariton Leaky-wave Antenna with Circular Polarization
Sajjad Zohrevand - Mohammad Amin Chaychi zadeh - Nader Komjani
Enhancing Brain Tumor Classification in OCT Images using Local Phase Quantization Features
Naeem Eslamyeh Hamedani - Hasti Shabani
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 41.7.4