لطفا منتظر بمانید ...
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
Novel Low Power Switch-Count Structure for Medium/High Power Multilevel Inverter
Ali Seifi - Seyed-hossein Hosseini - Mehrdad Tarafdar Hagh
Graphene-Based Slot Antenna with Improved Bandwidth for 6G Terahertz Communications
Alireza Tahvildari - Aslan Nouri Moqadam - Shokrollah Karimian
Controlling Energy Consumption and Intelligent Manufacturing through an Energy-aware Scheduling Algorithm in Industrial Sector
Negin Shafinezhad - Maryam Mahmoudi - Hamid Abrishami - Vahid Baghishani
اولویتبندی کلیدهای قدرت جهت پیادهسازی سیستم پایش وضعیت
محمدرضا قطبالدینی - احمد میرزائی - محمدمهدی منصوری مجومرد
طراحی و شبیه سازی یک تقویت کننده کم نویز پهن باند در باند K (18 تا 27 گیگاهرتز)
نوید نصیری - حسین شمسی
Design of Fresnel-Region Millimeter-Wave Metasurface Beam Shaper Using Deep Learning
Mohammad Hossein Koohi Ghamsari - Ehsan Imanbeygi - Mehdi Ahmadi-Boroujeni
Reliability-Based Design of Time-Varying Electricity Tariff
Mohammad Rastegar - Nima Sarajpoor
DWT-Based Epileptic Seizure Detection Using Fuzzy Logic Model with Entropy and Table Lookup Scheme
Alireza Mohammadi - Arvin Esfandyari - Ali Doustmohammadi - Amir Abolfazl Suratgar - Masoud Shafiee
A Two-Stage Hierarchical Deep Learning Model for Inter-Patient Arrhythmia Classification
Mohammad Ahmadabadi - Ali Sadr
External Force Control with Disturbance Rejection for 6 DoF Manipulator
Zahra Bonakdar - Arefe Hamidipour - Hamed Ghafarirad
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.7.2