0% Complete
صفحه اصلی
/
سی و دومین کنفرانس بین المللی مهندسی برق
Active Data Fusion in Deep Neural Networks via Separation Index
نویسندگان :
Movahed Jamshidi
1
Ahmad Kalhor
2
Abdol-Hossein Vahabie
3
1- دانشگاه تهران
2- دانشگاه تهران
3- دانشگاه تهران
کلمات کلیدی :
feature fusion،Separation Index (SI)،feature selection،deep neural networks
چکیده :
In this paper, we aim to enhance Convolutional Neural Networks (CNNs) by merging features from different pretrained models to improve information representation. Amidst advancements in network depth and architectures, we highlight feature fusion as a method for boosting CNN performance. Despite challenges in managing large feature sets and potential information loss during fusion, our paper introduces the Separation Index (SI) for feature selection. Unlike passive fusion, where all feature maps are simply concatenated, we employ the SI metric for active fusion. This method selects informative and discriminative features for the classification task, reducing computational complexity and model sizes. We evaluate our approach using medical and public datasets, specifically Skin Cancer data and CIFAR-10. The results demonstrate significant improvements in classification performance, confirming the effectiveness of our method. Notably, achieving a 95.63% classification accuracy on the CIFAR-10 dataset showcases the superiority of our approach over baselines and other competing methods.
لیست مقالات
لیست مقالات بایگانی شده
An Enhanced Chaotic System Based Color Image Encryption using DNA Encoding
Mobin Vaziri - Mohammad Mehdi Rahimifar - Hadi Jahanirad
Application of Max Flow- Min Cut Theory to find the best placement Of Electronic-based DC-PFCs for enhancing static security in MT-HVDC Meshed Grids
Mir Hamed Pour Mir Asghariyan - Jafar Milimonfared - Seyed Saeid Heidari Yazdi - Ali Haji Ali Biglo - Kumars Rouzbehi
A High Dynamic Range Differential Rectifier for RF Energy Harvesting
Ataollah Mahsafar - Mohammad Yavari
An Open-Loop Time Amplifier With Zero-Gain Delay in Output for Coarse-Fine Time to Digital Converters
Seyyed Morteza Golzan - Jafar Sobhi - Ziaddin Daie Koozehkanani
تولید پایگاه داده مصنوعی برای مقره های الکتریکی از روی دادههای تصویری با استفاده از شبکههای مولد تخاصمی
امیرحسین جراره - ابولفضل منافی - سعید شمقدری
Adaptive Control of Telerehabilitation Systems in The Framework of Multi-Agent Systems
Mohammadreza Sheykh - Heidar Ali Talebi - ّIman Sharifi
A New Approch on Condition Assessment of MV Switchgear based on Thermal Evaluation
Mohsen Taghizadeh Kejani - Seyed Hamid Khalkhali - Ali asghar RaziKazemi
Selenium Doped Hafnium Disulfide Alloy for Visible Photodetection
Mohammadreza Razeghizadeh - Mohsen Mazaherifar - Mahdi Pourfath
شبیه سازی رفتار و عملکرد مقره پلیمری 20 کیلوولت با اعمال آلودگی سطحی از نقطه نظر ارزیابی و سنجش جریان خزشی و ارائه الگوی معادل سازی آن
سیدمحمدعلی طباطبائی - حمید جوادی - مسعود عبدالحسین پور - فرامرز قلیچی
Synergy of Deep Learning and Artificial Potential Field Methods for Robot Path Planning in the Presence of Static and Dynamic Obstacles
Mohammad Amin Basiri - Shirin Chehelgami - Erfan Ashtari - Mehdi Tale Masouleh - Ahmad Kalhor
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 43.6.0
