Ivica Dimitrovski

Prof. Dr. Ivica Dimitrovski

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
8 June 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
IDIvica Dimitrovski
Ivica Dimitrovski
VSVlatko Spasev
Vlatko Spasev
SLSuzana Loshkovska
Suzana Loshkovska
IKIvan Kitanovski
Ivan Kitanovski
Semantic segmentation of remote sensing imagery stands as a fundamental task within the domains of both remote sensing and computer vision. Its objective is to generate a comprehensive pixel-wise segmentation map of an image, assigning a specific label to each pixel. This facilitates in-depth analysis and comprehension of the Earth’s surface. In this paper, we propose an approach for enhancing semantic segmentation performance by employing an ensemble of U-Net models with three different backbone networks: Multi-Axis Vision Transformer, ConvFormer, and EfficientNet. The final segmentation maps are generated through a geometric mean ensemble method, leveraging the diverse representations learned by each backbone network. The effectiveness of the base U-Net models and the proposed ensemble is evaluated on multiple datasets commonly used for semantic segmentation tasks in remote sensing imagery, including LandCover.ai, LoveDA, INRIA, UAVid, and ISPRS Potsdam datasets. Our experimental results demonstrate that the proposed approach achieves state-of-the-art performance, showcasing its effectiveness and robustness in accurately capturing the semantic information embedded within remote sensing images.

1 January 2015 in Computerized Medical Imaging and Graphics
Verified
Journal Article
Closed access
IDIvica Dimitrovski
Ivica Dimitrovski
Dragi KocevDragi Kocev
Dragi Kocev
IKIvan Kitanovski
Ivan Kitanovski
SLSuzana Loskovska
Suzana Loskovska
SDSašo Džeroski
Sašo Džeroski

29 May 2015
Verified
Book Chapter
Closed access
PDF file
DSDario Stojanovski
Dario Stojanovski
GSGjorgji Strezoski
Gjorgji Strezoski
GMGjorgji Madjarov
Gjorgji Madjarov
IDIvica Dimitrovski
Ivica Dimitrovski

25 January 2016 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
IKIvan Kitanovski
Ivan Kitanovski
GSGjorgji Strezoski
Gjorgji Strezoski
IDIvica Dimitrovski
Ivica Dimitrovski
GMGjorgji Madjarov
Gjorgji Madjarov
SLSuzana Loskovska
Suzana Loskovska

5 March 2025
Verified
Book Chapter
Closed access
PDF file
VSVlatko Spasev
Vlatko Spasev
IDIvica Dimitrovski
Ivica Dimitrovski
ICIvan Chorbev
Ivan Chorbev
IKIvan Kitanovski
Ivan Kitanovski

16 January 2024 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
IDIvica Dimitrovski
Ivica Dimitrovski
IKIvan Kitanovski
Ivan Kitanovski
NSNikola Simidjievski
Nikola Simidjievski
Dragi KocevDragi Kocev
Dragi Kocev
We investigate the utility of in-domain self-supervised pretraining of vision models in the analysis of remote sensing imagery. Self-supervised learning (SSL) has emerged as a promising approach for remote sensing image classification due to its ability to exploit large amounts of unlabeled data. Unlike traditional supervised learning, SSL aims to learn representations of data without the need for explicit labels. This is achieved by formulating auxiliary tasks that can be used for pretraining models before fine-tuning them on a given downstream task. A common approach in practice to SSL pretraining is utilizing standard pretraining datasets, such as ImageNet. While relevant, such a general approach can have a suboptimal influence on the downstream performance of models, especially on tasks from challenging domains such as remote sensing. In this letter, we analyze the effectiveness of SSL pretraining by employing the image bidirectional encoder representations from transformers (BERT) pretraining with online tokenizer (iBOT) framework coupled with Vision transformers (ViTs) trained on million aerial image dataset (Million-AID), a large and unlabeled remote sensing dataset. We present a comprehensive study of different self-supervised pretraining strategies and evaluate their effect across 14 downstream datasets with diverse properties. Our results demonstrate that leveraging large in-domain datasets for self-supervised pretraining consistently leads to improved predictive downstream performance, compared to the standard approaches found in practice.