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
Design and fabrication of wearable and stretchable EEG headband using textile-based electrode wire
Kourosh Motiepor - Arman Modoudi Yaghouti - Simin Bakhtiyari - Amir Jahanshahi - Roohollah Bagherzadeh
Temperature-Sensitive Tunable Nanoantenna Based on Phase Change Material (Ge2Sb2Te5) Substrate
Daniyal Khosh Maram - Seyed Asad Amirhosseini
Better Exploration In Single-Agent Q-Learning Using Controlled Linear Perturbation
Sadredin Hokmi - Mohammad Haeri
Inversion Coefficient as a Key Design Parameter in MOS Device Performance
Gholamreza Khademevatan - Ali Jalali
A brief review of methods for improving the performance of virtual synchronous generators under unbalnced conditions
Mohammad Hossein Mousavi - Hassan Moradi CheshmehBeigi
A straightforward approach for measuring blood pressure in an upper arm digital blood pressure monitor
Mohammad Soroush Rezaei - Mahdi Khalilzadeh Shabestari - Seyed Yousef Jazaery Farsany - Danial Katoozian - Hossein Hosseini-Nejad
Batch(offline) Reinforcement Learning for recommender system
Mohammad Amir Rezaei Gazik - Mehdy Roayaei
A Novel Estimation Law for Impedance-Controlled Bilateral Teleoperation to Enhance Human-Environment Interaction
Mobina Kameli - Mohammad Motaharifar - Negin Sayyaf
پیاده سازی و بهبود عملکرد شبکه اینترنت اشیا سلولی بر بستر پروژه منبع باز OAI
سیدمحمدرضا طباطبایی نژاد - حسین خالقی بیزکی - سجاد پورسجادی
Data Association and Multi-Target Localization Using Particle Swarm Optimization
Seyed Mohammad B. Seyedin - Fereidoon Behnia
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 40.4.2