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
Multiphysics Simulation of the Modified Flux Coupling Type SFCL in VSC-HVDC Network
Mohammad Khakroei - Ashkan Mirzaei Rajeooni - Mahdi Rahimi Pirbasti - Hossein Heydari
A COMPREHENSIVE DEEP LEARNING METHOD for SHORT-TERM LOAD FORECASTING
Mohammad Sayadlou - Mahdi Salay naderi - Mehrdad Abedi - Sajad Esmaeili - Mohammad Amini
Counterintuitive Benefits of Time Window Constraints: Enhancing Cost Efficiency in Vehicle Routing Problems
Mehdi Alimohammadi - Saeedeh Rezaee - Nasser Motahari Farimani - Mohammad Reza Akbarzadeh Totonchi
ساخت یک تراشه میکروسیالی برای شمارش سلول های معلق در مایع با الکترود های مایع
نرگس حسین زاده - پادینا فرخیان - سیدعلی حسینی
Optimal Placement of Followers Within the Convex Hull of Leaders: A Distributed Subgradient Approach
Seyedeh Mahsa Zakipour Bahambari - Saeed Khankalantary
امکانسنجی اقتصادی استقرار شبکههای مخابرات صنعتی در شرکت توزیع نیروی برق شهرستان مشهد (با تاکید بر نقش هوشمندسازی شبکه و بکارگیری انرژیهای سبز)
مهدی فیل سرائی - مهدی اسماعیلی پور - علیرضا باوندپور
Attractors Manipulation in Denoising Autoencoders for Robust Phone Recognition
Shaghayegh Reza - Seyyed Ali Seyyedsalehi - Seyyedeh Zohreh Seyyedsalehi
Analysis of an E-core Permanent Magnet Switched Reluctance Motor
Ali Ghaffarpour - Mojtaba Mirsalim
Stray Load Losses Determination Methods of Induction Motors-A Review
Moslem Geravandi - Hassan Moradi CheshmehBeigi
An Integrated Technical Analysis and Machine Learning Trading Model for Noisy and Volatile Financial Markets
Arvin Esfandiari - Ali Doustmohammadi
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.3