Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed

Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741

Browse

Start date: 2020Type: search.filters.itemtype.Conference PaperSubject: search.filters.subject.Convolutional Neural NetworksAuthor: search.filters.author.Arica, Nafiz

Search Results

Now showing 1 - 4 of 4
  • No Thumbnail Available
    PublicationMetadata only
    Effects of Network Depths on Semantic Image Segmentation by Weakly Supervised Learning, Zayif Denetimli Ogrenmeyle Semantik Imge Bolutlemede Ag Derinliginin Etkileri
    (Institute of Electrical and Electronics Engineers Inc., 2020) Bircanoglu, Cenk; Arica, Nafiz; Bircanoglu, Cenk, Adevinta, Paris, France; Arica, Nafiz, Bahçeşehir Üniversitesi, Istanbul, Turkey
    Weakly Supervised Learning is one of the most interesting approaches that more complex labels are predicted by using related simple labels. In this study, we focus on segmentation problem by giving image class tags in learning stage. We examine how the number of layers and the usage of their output in Convolutional Neural Network affect the segmentation results. It is found that increasing the number of layers in the network has a positive effect on segmentation performance. After ResNet152 is determined as the most successful deep architecture in Pascal VOC2012 dataset, we construct a new architecture based on ResNet152. Experimental results show that proposed architecture outperforms the available studies tested on this particular dataset. In addition, we observe that early layers reach more general attributes for the object classes than the last layers and that these attributes can better identify the object boundaries. © 2021 Elsevier B.V., All rights reserved.
  • No Thumbnail Available
    PublicationMetadata only
    A Scoring Method for Interpretability of Concepts in Convolutional Neural Networks, Evrişimsel Sinir Aǧlarinda Kavram Yorumlama için bir Puanlama Yöntemi
    (Institute of Electrical and Electronics Engineers Inc., 2022) Gurkan, Mustafa Kaǧan; Arica, Nafiz; Vural, Fatos T.Yarman; Gurkan, Mustafa Kaǧan, Bahçeşehir Üniversitesi, Istanbul, Turkey; Arica, Nafiz, Bahçeşehir Üniversitesi, Istanbul, Turkey; Vural, Fatos T.Yarman, Middle East Technical University (METU), Ankara, Turkey
    In this paper, we propose a scoring algorithm for measuring the interpretability of CNN models by focusing on the feature extraction operation at the convolutional layers. The proposed approach is based on the principal of concept analysis, for a predefined list of concepts. A map of the network is created based on its responsiveness against each concept. Once this map is ready, various images can be applied as inputs and they are matched with the concepts whose hidden nodes are highly activated. Finally, the evaluation algorithm kicks in to use these descriptions during the final prediction and provides human-understandable explanations. © 2022 Elsevier B.V., All rights reserved.
  • No Thumbnail Available
    PublicationMetadata only
    Creation of Annotated Synthetic UAV Video Dataset for Object Detection and Tracking, Nesne Tespit ve Takibi için Etiketli Yapay IHA Video Veriseti Yaratimi
    (Institute of Electrical and Electronics Engineers Inc., 2023) Yilmaz, Can; Maraş, Bahri; Arica, Nafiz; Ertüzün, Ayşin Baytan; Yilmaz, Can, Yapay Zeka Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Maraş, Bahri, Elektrik Ve Elektronik Mühendisliǧi Bölümü, Boğaziçi Üniversitesi, Bebek, Turkey; Arica, Nafiz, Bilişim Sistemleri Mühendisliǧi Bölümü, Pîrî Reis Üniversitesi, Istanbul, Turkey; Ertüzün, Ayşin Baytan, Elektrik Ve Elektronik Mühendisliǧi Bölümü, Boğaziçi Üniversitesi, Bebek, Turkey
    In order for object detection and tracking in videos obtained from unmanned aerial vehicles (UAVs) by deep convolutional neural networks (DCNN), extensive ground truth optical flow, occlusion and segmentation datasets, of various objects or vehicles, are required during the training and testing processes. The mentioned ground truth informations are not widely available in the literature due to the difficulty of labeling or extracting them from real-life recorded UAV video images. In this study, ground truth optical flow, occlusion and segmentation datasets were produced synthetically for the first time with the UAV point of view in a novel way, so as to fill the gap in literature. The ground truth datasets were created for each vehicle by subjecting the triangles (mesh) automatically generated by the Unity engine to the homography method. With this method, 1920x1080 and 250x250 sized synthetic datasets consisting of 100 scenarios were obtained. © 2023 Elsevier B.V., All rights reserved.
  • No Thumbnail Available
    PublicationMetadata only
    Enhancing Object Detection Algorithms by Synthetic Aerial Images, Yapay Hava Imgeleriyle Nesne Tespit Algoritmalarinin Güçlendirilmesi
    (Institute of Electrical and Electronics Engineers Inc., 2023) Yilmaz, Can; Maraş, Bahri; Yilmaz, Görkem; Ceylan, Göksu; Hamamcioǧlu, Önder; Arica, Nafiz; Ertüzün, Ayşin Baytan; Yilmaz, Can, Yapay Zeka Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Maraş, Bahri, Elektrik Ve Elektronik Mühendisliǧi Bölümü, Boğaziçi Üniversitesi, Bebek, Turkey; Yilmaz, Görkem, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Ceylan, Göksu, Yapay Zeka Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Hamamcioǧlu, Önder, Bilgisayar Mühendisliǧi Bölümü, Bahçeşehir Üniversitesi, Istanbul, Turkey; Arica, Nafiz, Bilişim Sistemleri Mühendisligi Bölümü, Pîrî Reis Üniversitesi, Istanbul, Turkey; Ertüzün, Ayşin Baytan, Elektrik Ve Elektronik Mühendisliǧi Bölümü, Boğaziçi Üniversitesi, Bebek, Turkey
    In order to accurately perform object detection by deep convolutional neural networks (DCNN) in videos, obtained from unmanned aerial vehicles (UAVs), many example images of objects containing annotations such as ground truth class information, bounding box, optical flow, occlusion and segmentation are required. Due to the difficulties faced during annotation of scenarios, and due to the inadequacy of the scenario diversity resulting from environmental conditions, a dataset containing above mentioned ground truths has not been found in the literature. In this study, synthetic aerial images with various annotation information were created in different scenarios while composing virtual worlds, and enhancing object detection algorithms is aimed. Enhancement of detection results of DCNN based object detection algorithms, trained with the support of synthetic aerial images, on real-world aerial images significantly, was observed during the experiments, conducted. © 2023 Elsevier B.V., All rights reserved.