Nafiz Arica
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Nafiz Arica has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
- Kadir Alpaslan Demir
Department of Computer Sciences, Texas A&M University–Corpus Christi, Corpus Christi, TX 78412, USA
4 shared publications Anil Celik
Bilgisayar Mühendisliği Bölümü, Bahçeşehir Üniversitesi, İstanbul, Türkiye
3 shared publications- Duygu Cakir
Department of Software Engineering, Bahcesehir University, Istanbul, Turkey
3 shared publications Emrah Ergul
Electronics and Communication Engineering Department, Kocaeli University, İzmit, Turkey
3 shared publicationsF.T. Yarman-Vural
3 shared publicationsAlper Yorukcu
Computer Science Department Carleton University Ottawa Canada
2 shared publications
Latest Publications
- Open Access
- 11 January 2025
- Published by Springer Nature in Machine Vision and Applications
- Vol. 36 (2) , 1-17
A concept-aware explainability method for convolutional neural networks
Although Convolutional Neural Networks (CNN) outperform the classical models in a wide range of Machine Vision applications, their restricted interpretability and their lack of comprehensibility in reasoning, generate many problems such as security, reliability, and safety. Consequently, there is a growing need for research to improve explainability and address their limitations. In this paper, we propose a concept-based method, called Concept-Aware Explainability (CAE) to provide a verbal explanation for the predictions of pre-trained CNN models. A new measure, called detection score mean, is introduced to quantify the relationship between the filters of the model and a set of pre-defined concepts. Based on the detection score mean values, we define sorted lists of Concept-Aware Filters (CAF) and Filter-Activating Concepts (FAC). These lists are used to generate explainability reports, where we can explain, analyze, and compare models in terms of the concepts embedded in the image. The proposed explainability method is compared to the state-of-the-art methods to explain Resnet18 and VGG16 models, pre-trained on ImageNet and Places365-Standard datasets. Two popular metrics, namely, the number of unique detectors and the number of detecting filters, are used to make a quantitative comparison. Superior performances are observed for the suggested CAE, when compared to Network Dissection (NetDis) (Bau et al., in: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2017), Net2Vec (Fong and Vedaldi, in: Paper presented at IEEE conference on computer vision and pattern recognition (CVPR), 2018), and CLIP-Dissect (CLIP-Dis) (Oikarinen and Weng, in: The 11th international conference on learning representations (ICLR), 2023) methods.
- 11 January 2025
- Published by Springer Nature in Machine Vision and Applications
- Vol. 36 (2) , 1-17
Open AccessA concept-aware explainability method for convolutional neural networks
Although Convolutional Neural Networks (CNN) outperform the classical models in a wide range of Machine Vision applications, their restricted interpretability and their lack of comprehensibility in reasoning, generate many problems such as security, reliability, and safety. Consequently, there is a growing need for research to improve explainability and address their limitations. In this paper, we propose a concept-based method, called Concept-Aware Explainability (CAE) to provide a verbal explanation for the predictions of pre-trained CNN models. A new measure, called detection score mean, is introduced to quantify the relationship between the filters of the model and a set of pre-defined concepts. Based on the detection score mean values, we define sorted lists of Concept-Aware Filters (CAF) and Filter-Activating Concepts (FAC). These lists are used to generate explainability reports, where we can explain, analyze, and compare models in terms of the concepts embedded in the image. The proposed explainability method is compared to the state-of-the-art methods to explain Resnet18 and VGG16 models, pre-trained on ImageNet and Places365-Standard datasets. Two popular metrics, namely, the number of unique detectors and the number of detecting filters, are used to make a quantitative comparison. Superior performances are observed for the suggested CAE, when compared to Network Dissection (NetDis) (Bau et al., in: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), 2017), Net2Vec (Fong and Vedaldi, in: Paper presented at IEEE conference on computer vision and pattern recognition (CVPR), 2018), and CLIP-Dissect (CLIP-Dis) (Oikarinen and Weng, in: The 11th international conference on learning representations (ICLR), 2023) methods.
- 16 December 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (5) , 3777-3791
Enhanced facial action unit detection with adaptable patch sizes on representative landmarks
- 16 December 2024
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (5) , 3777-3791
Enhanced facial action unit detection with adaptable patch sizes on representative landmarks
- 25 June 2024
- Published by Springer Nature
- p. 101-111
Style Transfer to Enhance Data Augmentation for Facial Action Unit Detection
- 25 June 2024
- Published by Springer Nature
- p. 101-111
Style Transfer to Enhance Data Augmentation for Facial Action Unit Detection
- Open Access
- 20 October 2023
- Published by Elsevier in Engineering Science and Technology, an International Journal
- Vol. 47
Cascading CNNs for facial action unit detection
- 20 October 2023
- Published by Elsevier in Engineering Science and Technology, an International Journal
- Vol. 47
Open AccessCascading CNNs for facial action unit detection
- 28 July 2023
- Published by Springer Nature in Machine Vision and Applications
- Vol. 34 (5) , 1-22
A robust vehicle tracking in low-altitude UAV videos
- 28 July 2023
- Published by Springer Nature in Machine Vision and Applications
- Vol. 34 (5) , 1-22
A robust vehicle tracking in low-altitude UAV videos
- Open Access
ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation
Weakly Supervised Semantic Segmentation (WSSS) is a challenging task aiming to learn the segmentation labels from class-level labels. In the literature, exploiting the information obtained from Class Activation Maps (CAMs) is widely used for WSSS studies. However, as CAMs are obtained from a classification network, they are interested in the most discriminative parts of the objects, producing non-complete prior information for segmentation tasks. In this study, to obtain more coherent CAMs with segmentation labels, we propose a framework that employs an iterative approach in a modified encoder-decoder-based segmentation model, which simultaneously supports classification and segmentation tasks. As no ground-truth segmentation labels are given, the same model also generates the pseudo-segmentation labels with the help of dense Conditional Random Fields (dCRF). As a result, the proposed framework becomes an iterative self-improved model. The experiments performed with DeepLabv3 and UNet models show a significant gain on the Pascal VOC12 dataset, and the DeepLabv3 application increases the current state-of-the-art metric by %2.5. The implementation associated with the experiments can be found: https://github.com/cenkbircanoglu/isim.
Open AccessISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation
Weakly Supervised Semantic Segmentation (WSSS) is a challenging task aiming to learn the segmentation labels from class-level labels. In the literature, exploiting the information obtained from Class Activation Maps (CAMs) is widely used for WSSS studies. However, as CAMs are obtained from a classification network, they are interested in the most discriminative parts of the objects, producing non-complete prior information for segmentation tasks. In this study, to obtain more coherent CAMs with segmentation labels, we propose a framework that employs an iterative approach in a modified encoder-decoder-based segmentation model, which simultaneously supports classification and segmentation tasks. As no ground-truth segmentation labels are given, the same model also generates the pseudo-segmentation labels with the help of dense Conditional Random Fields (dCRF). As a result, the proposed framework becomes an iterative self-improved model. The experiments performed with DeepLabv3 and UNet models show a significant gain on the Pascal VOC12 dataset, and the DeepLabv3 application increases the current state-of-the-art metric by %2.5. The implementation associated with the experiments can be found: https://github.com/cenkbircanoglu/isim.
- 9 February 2022
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 47 (11) , 14025-14036
Forecasting of Day-Ahead Electricity Price Using Long Short-Term Memory-Based Deep Learning Method
- 9 February 2022
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 47 (11) , 14025-14036
Forecasting of Day-Ahead Electricity Price Using Long Short-Term Memory-Based Deep Learning Method
- 21 September 2021
- Published by Springer Nature in The Visual Computer
- Vol. 38 (12) , 4235-4250
Stacking multiple cues for facial action unit detection
- 21 September 2021
- Published by Springer Nature in The Visual Computer
- Vol. 38 (12) , 4235-4250
Stacking multiple cues for facial action unit detection
- 1 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Auto-encoder based cognitive analysis of questionnary
In this study we propose a new method for Likert scale questionnary data analysis using auto-encoders. The proposed method extracts the patterns, which maximally activate the neurons of the hidden layer in the auto-encoder, trained by the questionnary data. These patterns are thought to be cognitive patterns that are influenced by participants filling the questionnary. In the experiments, we employ a questionnary designed to measure the confidence level of a blog author on the web. The cognitive patterns obtained in the auto-encoder are considered as the components that form the general approaches of the participants. In two cognitive patterns drawn from the questionnary, it is observed that the blogger's expertise, integrity, benevolance are evaluated in decreasing or increasing order by the participants. It has also been observed that the proposed method can be used to correct the unintentional mistakes in questionnary answers.
- 1 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Auto-encoder based cognitive analysis of questionnary
In this study we propose a new method for Likert scale questionnary data analysis using auto-encoders. The proposed method extracts the patterns, which maximally activate the neurons of the hidden layer in the auto-encoder, trained by the questionnary data. These patterns are thought to be cognitive patterns that are influenced by participants filling the questionnary. In the experiments, we employ a questionnary designed to measure the confidence level of a blog author on the web. The cognitive patterns obtained in the auto-encoder are considered as the components that form the general approaches of the participants. In two cognitive patterns drawn from the questionnary, it is observed that the blogger's expertise, integrity, benevolance are evaluated in decreasing or increasing order by the participants. It has also been observed that the proposed method can be used to correct the unintentional mistakes in questionnary answers.