Marjan Stoimchev
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Marjan Stoimchev has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Dragi Kocev
Jožef Stefan Institute, Ljubljana, Slovenia
4 shared publications - Sašo Džeroski
Jozef Stefan Institute
4 shared publications - Jurica Levatić
Jozef Stefan Institute
3 shared publications - Boshko Koloski
Jožef Stefan Institute, Ljubljana, Slovenia
1 shared publication - Marija Ivanovska
Faculty of Electrical Engineering University of Ljubljana Tržaška cesta 25 1000 Ljubljana Slovenia
1 shared publication - Vitomir Štruc
Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia
1 shared publication
Latest Publications
- 15 May 2026
- Published by Elsevier in Information Sciences
- Vol. 754
Fully- and semi-supervised hierarchical multi-label image classification with graph learning
- 15 May 2026
- Published by Elsevier in Information Sciences
- Vol. 754
Fully- and semi-supervised hierarchical multi-label image classification with graph learning
- Open Access
- 9 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 14882-14896
SSL-MAE: Adaptive Semisupervised Learning Framework for Multilabel Classification of Remote Sensing Images Using Masked Autoencoders
The increasing volume of remotely sensed imagery (RSI) requires efficient processing and extraction of meaningful information. Modern deep learning architectures excel in various tasks but typically require large labeled datasets, which are often scarce in RSI due to the tedious labeling of complex heterogeneous landscapes containing multiple semantic categories. This can limit the potential of supervised deep learning methods. To address this, we propose SSL-MAE, a novel semi-supervised learning method based on a masked autoencoder. Our approach unifies self-supervision and discriminative learning within a single, end-to-end framework, leveraging both abundant unlabeled data and limited labeled data. Additionally, we introduce an adaptive mechanism to control the level of supervision during learning, crucial for balancing prediction quality with effective use of unlabeled data. To validate SSL-MAE's effectiveness, we conducted comprehensive experiments on 10 publicly available RSI datasets (5 multi-class and 5 multi-label classification). The results show that our method outperforms state-of-the-art semi-supervised methods and performs favorably against self-supervised methods when labeled data are scarce. Finally, our results suggest that the proposed adaptive joint learning strategy is not restricted to a single design choice; instead, when integrated with different state-of-the-art self-supervised approaches, it significantly enhances their predictive performance.
- 9 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 14882-14896
Open AccessSSL-MAE: Adaptive Semisupervised Learning Framework for Multilabel Classification of Remote Sensing Images Using Masked Autoencoders
The increasing volume of remotely sensed imagery (RSI) requires efficient processing and extraction of meaningful information. Modern deep learning architectures excel in various tasks but typically require large labeled datasets, which are often scarce in RSI due to the tedious labeling of complex heterogeneous landscapes containing multiple semantic categories. This can limit the potential of supervised deep learning methods. To address this, we propose SSL-MAE, a novel semi-supervised learning method based on a masked autoencoder. Our approach unifies self-supervision and discriminative learning within a single, end-to-end framework, leveraging both abundant unlabeled data and limited labeled data. Additionally, we introduce an adaptive mechanism to control the level of supervision during learning, crucial for balancing prediction quality with effective use of unlabeled data. To validate SSL-MAE's effectiveness, we conducted comprehensive experiments on 10 publicly available RSI datasets (5 multi-class and 5 multi-label classification). The results show that our method outperforms state-of-the-art semi-supervised methods and performs favorably against self-supervised methods when labeled data are scarce. Finally, our results suggest that the proposed adaptive joint learning strategy is not restricted to a single design choice; instead, when integrated with different state-of-the-art self-supervised approaches, it significantly enhances their predictive performance.
- Open Access
- 11 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-16
Semi-Supervised Multi-Label Classification of Land Use/Land Cover in Remote Sensing Images With Predictive Clustering Trees and Ensembles
The task of remote sensing image (RSI) classification has been studied extensively in the geoscience and remote sensing (RS) community. While deep learning methods have shown great success in solving this task, their reliance on large-scale labeled datasets is a serious limitation when dealing with complex labels and multiple semantic categories. The process of annotating such datasets can be time-consuming and tedious, leading to limited availability of labeled data and reduced performance of supervised learning methods. To address this issue, semi-supervised learning (SSL) methods can be applied, as they use both the limited labeled data and the abundant unlabeled data. In this article, we propose an effective SSL framework for RSI classification, which combines two key concepts. First, we employ a deep convolutional feature extractor to learn feature representations that encode the images into a lower dimensional feature space, capturing the rich semantic context present in RSI. Second, we utilize semi-supervised predictive clustering trees (PCTs) and ensembles thereof to learn from both the labeled and unlabeled data. To evaluate the effectiveness of the proposed framework, we compare it against several state-of-the-art self-supervised and semi-supervised methods from the literature. We conduct extensive experiments on ten publicly available land use/land cover RSI classification datasets: five for multiclass classification (MCC) and five for multi-label classification (MLC). The results demonstrate that the proposed framework has superior predictive performance compared to state-of-the-art methods from the literature, highlighting its effectiveness in semi-supervised RSI classification.
- 11 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-16
Open AccessSemi-Supervised Multi-Label Classification of Land Use/Land Cover in Remote Sensing Images With Predictive Clustering Trees and Ensembles
The task of remote sensing image (RSI) classification has been studied extensively in the geoscience and remote sensing (RS) community. While deep learning methods have shown great success in solving this task, their reliance on large-scale labeled datasets is a serious limitation when dealing with complex labels and multiple semantic categories. The process of annotating such datasets can be time-consuming and tedious, leading to limited availability of labeled data and reduced performance of supervised learning methods. To address this issue, semi-supervised learning (SSL) methods can be applied, as they use both the limited labeled data and the abundant unlabeled data. In this article, we propose an effective SSL framework for RSI classification, which combines two key concepts. First, we employ a deep convolutional feature extractor to learn feature representations that encode the images into a lower dimensional feature space, capturing the rich semantic context present in RSI. Second, we utilize semi-supervised predictive clustering trees (PCTs) and ensembles thereof to learn from both the labeled and unlabeled data. To evaluate the effectiveness of the proposed framework, we compare it against several state-of-the-art self-supervised and semi-supervised methods from the literature. We conduct extensive experiments on ten publicly available land use/land cover RSI classification datasets: five for multiclass classification (MCC) and five for multi-label classification (MLC). The results demonstrate that the proposed framework has superior predictive performance compared to state-of-the-art methods from the literature, highlighting its effectiveness in semi-supervised RSI classification.
- Open Access
- 16 January 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (2) , 538
Deep Network Architectures as Feature Extractors for Multi-Label Classification of Remote Sensing Images
Data in the form of images are now generated at an unprecedented rate. A case in point is remote sensing images (RSI), now available in large-scale RSI archives, which have attracted a considerable amount of research on image classification within the remote sensing community. The basic task of single-target multi-class image classification considers the case where each image is assigned exactly one label from a predefined finite set of class labels. Recently, however, image annotations have become increasingly complex, with images labeled with several labels (instead of just one). In other words, the goal is to assign multiple semantic categories to an image, based on its high-level context. The corresponding machine learning tasks is called multi-label classification (MLC). The classification of RSI is currently predominantly addressed by deep neural network (DNN) approaches, especially convolutional neural networks (CNNs), which can be utilized as feature extractors as well as end-to-end methods. After only considering single-target classification for a long period, DNNs have recently emerged that address the task of MLC. On the other hand, trees and tree ensembles for MLC have a long tradition and are the best-performing class of MLC methods, but need predefined feature representations to operate on. In this work, we explore different strategies for model training based on the transfer learning paradigm, where we utilize different families of (pre-trained) CNN architectures, such as VGG, EfficientNet, and ResNet. The architectures are trained in an end-to-end manner and used in two different modes of operation, namely, as standalone models that directly perform the MLC task, and as feature extractors. In the latter case, the learned representations are used with tree ensemble methods for MLC, such as random forests and extremely randomized trees. We conduct an extensive experimental analysis of methods over several publicly available RSI datasets and evaluate their effectiveness in terms of standard MLC measures. Of these, ranking-based evaluation measures are most relevant, especially ranking loss. The results show that, for addressing the RSI-MLC task, it is favorable to use lightweight network architectures, such as EfficientNet-B2, which is the best performing end-to-end approach, as well as a feature extractor. Furthermore, in the datasets with a limited number of images, using traditional tree ensembles for MLC can yield better performance compared to end-to-end deep approaches.
- 16 January 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (2) , 538
Open AccessDeep Network Architectures as Feature Extractors for Multi-Label Classification of Remote Sensing Images
Data in the form of images are now generated at an unprecedented rate. A case in point is remote sensing images (RSI), now available in large-scale RSI archives, which have attracted a considerable amount of research on image classification within the remote sensing community. The basic task of single-target multi-class image classification considers the case where each image is assigned exactly one label from a predefined finite set of class labels. Recently, however, image annotations have become increasingly complex, with images labeled with several labels (instead of just one). In other words, the goal is to assign multiple semantic categories to an image, based on its high-level context. The corresponding machine learning tasks is called multi-label classification (MLC). The classification of RSI is currently predominantly addressed by deep neural network (DNN) approaches, especially convolutional neural networks (CNNs), which can be utilized as feature extractors as well as end-to-end methods. After only considering single-target classification for a long period, DNNs have recently emerged that address the task of MLC. On the other hand, trees and tree ensembles for MLC have a long tradition and are the best-performing class of MLC methods, but need predefined feature representations to operate on. In this work, we explore different strategies for model training based on the transfer learning paradigm, where we utilize different families of (pre-trained) CNN architectures, such as VGG, EfficientNet, and ResNet. The architectures are trained in an end-to-end manner and used in two different modes of operation, namely, as standalone models that directly perform the MLC task, and as feature extractors. In the latter case, the learned representations are used with tree ensemble methods for MLC, such as random forests and extremely randomized trees. We conduct an extensive experimental analysis of methods over several publicly available RSI datasets and evaluate their effectiveness in terms of standard MLC measures. Of these, ranking-based evaluation measures are most relevant, especially ranking loss. The results show that, for addressing the RSI-MLC task, it is favorable to use lightweight network architectures, such as EfficientNet-B2, which is the best performing end-to-end approach, as well as a feature extractor. Furthermore, in the datasets with a limited number of images, using traditional tree ensembles for MLC can yield better performance compared to end-to-end deep approaches.
- Open Access
Learning to Combine Local and Global Image Information for Contactless Palmprint Recognition
In the past few years, there has been a leap from traditional palmprint recognition methodologies, which use handcrafted features, to deep-learning approaches that are able to automatically learn feature representations from the input data. However, the information that is extracted from such deep-learning models typically corresponds to the global image appearance, where only the most discriminative cues from the input image are considered. This characteristic is especially problematic when data is acquired in unconstrained settings, as in the case of contactless palmprint recognition systems, where visual artifacts caused by elastic deformations of the palmar surface are typically present in spatially local parts of the captured images. In this study we address the problem of elastic deformations by introducing a new approach to contactless palmprint recognition based on a novel CNN model, designed as a two-path architecture, where one path processes the input in a holistic manner, while the second path extracts local information from smaller image patches sampled from the input image. As elastic deformations can be assumed to most significantly affect the global appearance, while having a lesser impact on spatially local image areas, the local processing path addresses the issues related to elastic deformations thereby supplementing the information from the global processing path. The model is trained with a learning objective that combines the Additive Angular Margin (ArcFace) Loss and the well-known center loss. By using the proposed model design, the discriminative power of the learned image representation is significantly enhanced compared to standard holistic models, which, as we show in the experimental section, leads to state-of-the-art performance for contactless palmprint recognition. Our approach is tested on two publicly available contactless palmprint datasets—namely, IITD and CASIA—and is demonstrated to perform favorably against state-of-the-art methods from the literature. The source code for the proposed model is made publicly available.
Open AccessLearning to Combine Local and Global Image Information for Contactless Palmprint Recognition
In the past few years, there has been a leap from traditional palmprint recognition methodologies, which use handcrafted features, to deep-learning approaches that are able to automatically learn feature representations from the input data. However, the information that is extracted from such deep-learning models typically corresponds to the global image appearance, where only the most discriminative cues from the input image are considered. This characteristic is especially problematic when data is acquired in unconstrained settings, as in the case of contactless palmprint recognition systems, where visual artifacts caused by elastic deformations of the palmar surface are typically present in spatially local parts of the captured images. In this study we address the problem of elastic deformations by introducing a new approach to contactless palmprint recognition based on a novel CNN model, designed as a two-path architecture, where one path processes the input in a holistic manner, while the second path extracts local information from smaller image patches sampled from the input image. As elastic deformations can be assumed to most significantly affect the global appearance, while having a lesser impact on spatially local image areas, the local processing path addresses the issues related to elastic deformations thereby supplementing the information from the global processing path. The model is trained with a learning objective that combines the Additive Angular Margin (ArcFace) Loss and the well-known center loss. By using the proposed model design, the discriminative power of the learned image representation is significantly enhanced compared to standard holistic models, which, as we show in the experimental section, leads to state-of-the-art performance for contactless palmprint recognition. Our approach is tested on two publicly available contactless palmprint datasets—namely, IITD and CASIA—and is demonstrated to perform favorably against state-of-the-art methods from the literature. The source code for the proposed model is made publicly available.