0% Complete
صفحه اصلی
/
سی و یکمین کنفرانس بین المللی مهندسی برق
Connective Reconstruction-based Novelty Detection
نویسندگان :
Seyyed Morteza Hashemi
1
Parvaneh Aliniya
2
Parvin Razzaghi
3
1- دانشگاه تحصیلات تکمیلی علوم پایه زنجان
2- University of Nevada, Reno
3- دانشگاه تحصیلات تکمیلی علوم پایه زنجان
کلمات کلیدی :
Novelty class detection،Out-of-distribution detection،Computer vision،Deep learning
چکیده :
Detection of out-of-distribution samples is one of the critical tasks for real-world applications of computer vision. The advancement of deep learning has enabled us to analyze real-world data which contain unexplained samples, accentuating the need to detect out-of-distribution instances more than before. GAN-based approaches have been widely used to address this problem due to their ability to perform distribution fitting; however, they are accompanied by training instability and mode collapse. We propose a simple yet efficient reconstruction-based method that avoids adding complexities to compensate for the limitations of GAN models while outperforming them. Unlike previous reconstruction-based works that only utilize reconstruction error or generated samples, our proposed method simultaneously incorporates both of them in the detection task. Our model, which we call "Connective Novelty Detection" has two subnetworks, an autoencoder, and a binary classifier. The autoencoder learns the representation of the positive class by reconstructing them. Then, the model creates negative and connected positive examples using real and generated samples. Negative instances are generated via manipulating the real data, so their distribution is close to the positive class to achieve a more accurate boundary for the classifier. To boost the robustness of the detection to reconstruction error, connected positive samples are created by combining the real and generated samples. Finally, the binary classifier is trained using connected positive and negative examples. We demonstrate a considerable improvement in novelty detection over state-of-the-art methods on MNIST and Caltech-256 datasets.
لیست مقالات
لیست مقالات بایگانی شده
A Closed RF Wave-Applicator to Study the Biological Effects of Mobile Communication Systems
SeyedMilad Miri - Karim Mohammadpour-Aghdam
A 23.4-31.9 GHz Tunable RF-MEMS Impedance Matching Network for 5G Power Amplifier
Fazel Ziraksaz - Alireza Hassanzadeh
طراحی تقویت کننده توان موج میلی متری پهن باند در فناوری سی ماس برای کاربردهای نسل پنجم
سید محمد مهدی جعفری - صمد شیخایی
مقایسهگر پویا با قابلیت کار در شرایط زیر آستانه بر اساس منطق Pseudo-NMOS
سید سعید حسینی دولت آبادی - محسن جلالی
Performance Analysis of the Modified Flux-Coupling-Type SFCL in VSC-HVDC System
Mohammad Khakroei - Ashkan Mirzaei Rajeooni - Mahdi Rahimi Pirbasti - Hossein Heydari
An Improved Nonlinear Observer-Based Integrated Guidance and Control for Hypersonic Flight Vehicle with Angle Constraints
Seyedeh Mahsa Zakipour Bahambari - Saeed Khankalantary
تخمین کانال V2X با استفاده از CDP وفقی
الهام نادری مقدم - محمدعلی سبقتی - حسن زارعیان
A Simulation Case Study of THz Reflection Spectroscopy
Mitra Mirsalehi - Zahra Kavehvash - Mehdi Fardmanesh
A Novel Estimation Law for Impedance-Controlled Bilateral Teleoperation to Enhance Human-Environment Interaction
Mobina Kameli - Mohammad Motaharifar - Negin Sayyaf
طراحی ایستگاه شارژ سریع با در نظر گرفتن عدم قطعیت منابع تجدیدپذیر و مدیریت ریسک
محمد بزرگپور رودباری - میثم جعفری نوکندی - محمد هاشمی مصیر
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.4