Ivan Martinović

Dr. Ivan Martinović

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 June 2025 in Electronics
Verified
Journal Article
Open access
PDF file
IMIvan Martinović
Ivan Martinović
TSTomás de J. Mateo Sanguino
Tomás de J. Mateo Sanguino
JJJovana Jovanović
Jovana Jovanović
MJMihailo Jovanović
Mihailo Jovanović
Milena DjukanovicMilena Djukanovic
Milena Djukanovic
The increasing deployment of autonomous vehicles (AVs) has exposed critical vulnerabilities in traffic sign classification systems, particularly against adversarial attacks that can compromise safety. This study proposes a dual-purpose defense framework based on convolutional autoencoders to enhance robustness against two prominent white-box attacks: Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD). Experiments on the German Traffic Sign Recognition Benchmark (GTSRB) dataset show that, although these attacks can significantly degrade system performance, the proposed models are capable of partially recovering lost accuracy. Notably, the defense demonstrates strong capabilities in both detecting and reconstructing manipulated traffic signs, even under low-perturbation scenarios. Additionally, a feature-based autoencoder is introduced, which—despite a high false positive rate—achieves perfect detection in critical conditions, a tradeoff considered acceptable in safety-critical contexts. These results highlight the potential of autoencoder-based architectures as a foundation for resilient AV perception while underscoring the need for hybrid models integrating visual-language frameworks for real-time, fail-safe operation.

1 January 2025 in FACETS
Verified
Journal Article
Open access
IMIvan Martinović
Ivan Martinović
SMShitong Mao
Shitong Mao
MDMehdy Dousty
Mehdy Dousty
WLWuqi Li
Wuqi Li
MĐMilena Đukanović
Milena Đukanović
ESErvin Sejdić
Ervin Sejdić
Self-supervised learning enables the creation of algorithms that outperform supervised pre-training methods in numerous computer vision tasks. This paper provides a comprehensive overview of self-supervised learning applications across various X-ray modalities, including conventional X-ray, computed tomography, mammography, and dental X-ray. Apart from the application of self-supervised learning in the interpretation phase of X-ray images, the paper also emphasizes the critical role of self-supervised learning integration in the preprocessing and archiving phase. Furthermore, the paper explores the application of self-supervised learning in multi-modal scenarios, which represents a key future direction in developing machine learning-based applications across the field of medicine. Lastly, the paper addresses the main challenges associated with the development of self-supervised learning applications tailored for X-ray modalities. The findings from the reviewed literature strongly suggest that the self-supervised learning approach has the potential to be a “ game-changer”, enabling the elimination of the current situation where many machine learning-based systems are developed but few are deployed in daily clinical practice.

8 July 2025 in Journal of Imaging Informatics in Medicine
Verified
Journal Article
Closed access
PDF file
IMIvan Martinović
Ivan Martinović
MDMehdy Dousty
Mehdy Dousty
WLWuqi Li
Wuqi Li
MĐMilena Đukanović
Milena Đukanović
JCJames L. Coyle
James L. Coyle
ESErvin Sejdić
Ervin Sejdić

1 January 2019 in Tehnika
Verified
Journal Article
Open access
PDF file
IMIvan Martinović
Ivan Martinović
In this paper, we presented the concept of negative resistance in a simplified way. Although the negative resistance was noticed even in the 19th century, it still causes inconveniences due to its absence as a discrete component. In this paper, the negative resistance was realized using a negative impedance converter. To understand clearly its influence in the electric circuit, a voltage divider circuit was used, which was analyzed both numerically and symbolically. The numerical analysis was performed in the simulation program LTspice, while the symbolic analysis was conducted in the Wolfram Mathematica software package. First, a voltage difference circuit with a positive resistor value was analyzed, after that one of the resistors was replaced with a negative resistance resistor. Additionally, simulations for the positive and negative equivalent resistance of the circuits were performed. Finally, the practical realization of the voltage divider circuit was demonstrated in order to make this concept more complete.