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
Secrecy Sum Rate Analysis and Power Allocation with OSTBC and Artificial Noise for MIMO Systems
Abdolrasoul Sakhaei Gharagezlou - Mahdi Nangir - Nima Imani - Amir Poorfaraj Liqvan
Numerical Study of a Microfluidic-Based Motile Sperm Enrichment Using Sperm Rheotactic Behavior
Mohammadjavad Bouloorchi - Saeed Javadizadeh - Aref Valipour - MirBehrad Mousavi - Majid Badieirostami
Classifying Human Spatial Navigation Anxiety Using Electrooculography Signals and Machine Learning Techniques
Saeed Mousavi - Sara Ashrafi - Mehdi Delrobaei
بررسی تاثیر دینامیکی سیستمهای انرژی خورشیدی متصل به شبکه بر بارگذاری ترانسفورماتور و بهبود عملکرد شبکه فشار ضعیف توزیع نیروی برق
مهدی محمدی - رضا خدادی - علی معصومی
Stability Improvement in Weak Grid-Tied DFIG-based WECS Employing Adaptive Virtual Impedance Strategy Based on Machine Learning Considering the LVRT Constraint
Mohammad Hossein Shaabani - Behrooz Vahidi - Navid Dehghan
Design of a highly efficient photoconductive terahertz modulator enhanced by photonic crystal resonant cavity
Faramarz Alihosseini - Zahra Heshmatpanah - Hesam Zandi
Multi-Attribute Decision-Making Methods to a Cloud Service Providing Selection
Amirhossein Shahbakhsh razavi - Kiumars Javan - Mehdi Zaferanieh - Somayeh Sobati-Moghadam
Speech Emotion Recognition Using Transfer Learning and Self-Supervised Speech Representation Learning
Marziye Azad - Babak Nasersharif
Wideband and Multi-band Frequency Selective Surfaces for Microwave Shielding
Mahmoodreza Marzban - Abbas Alighanbari
CNN-LSTM model for Confusion Classification; using Single-Channel EEG
Amirhossein Aran - Zahra Ghanbari - Mohammad Hassan Moradi
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.3