M. Sc. Minh Tuan Pham

Methods for Intelligent Interactive Systems (I2S)

Telefon: +49 561 804-6017
E-Mail: tuan.pham[at]uni-kassel[dot]de

Standort: Wilhelmshöher Allee 73
34121 Kassel

Raum: WA-altes Gebäude (WA 73), ohne Raumangabe

Publikationen

[ 2024 ]
[ 2023 ]
[ 2022 ]
[ 2021 ]
[ 2019 ]

2024[ to top ]

Workshop on Interactive Adaptive Learning (IAL), ECML PKDD. Bunse, Mirko; Herde, Marek; Krempl, Georg; Lemaire, Vincent; Tharwat, Alaa; Pham, Minh Tuan; Saadallah, Amal. In Vol. 3770CEUR Workshop Proceedings. 2024.
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
@proceedings{bunse2024workshop, editor = {Bunse, Mirko and Herde, Marek and Krempl, Georg and Lemaire, Vincent and Tharwat, Alaa and Pham, Minh Tuan and Saadallah, Amal}, keywords = {itegpub}, series = {{CEUR} Workshop Proceedings}, title = {Workshop on Interactive Adaptive Learning (IAL), ECML PKDD}, volume = 3770, year = 2024 }
%0 Conference Proceedings %1 bunse2024workshop %B CEUR Workshop Proceedings %D 2024 %E Bunse, Mirko %E Herde, Marek %E Krempl, Georg %E Lemaire, Vincent %E Tharwat, Alaa %E Pham, Minh Tuan %E Saadallah, Amal %T Workshop on Interactive Adaptive Learning (IAL), ECML PKDD %U http://ceur-ws.org/Vol-3770 %V 3770
Tutorial: Interactive Adaptive Learning. Herde, Marek; Pham, Minh Tuan; Tharwat, Alaa; Sick, Bernhard. In Workshop on Interactive Adapative Learning (IAL), ECML PKDD, bll 1–6. 2024.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
We summarize the contents of the tutorial we present as a part of the 8th Interactive Adaptive Learning workshop. This workshop is co-located with the ECML-PKDD conference, where it takes place on September 9th, 2024 in Vilnius, Lithuania.
@inproceedings{herde2024tutorial, abstract = {We summarize the contents of the tutorial we present as a part of the 8th Interactive Adaptive Learning workshop. This workshop is co-located with the ECML-PKDD conference, where it takes place on September 9th, 2024 in Vilnius, Lithuania.}, author = {Herde, Marek and Pham, Minh Tuan and Tharwat, Alaa and Sick, Bernhard}, booktitle = {Workshop on Interactive Adapative Learning (IAL), ECML PKDD}, keywords = {itegpub}, pages = {1–6}, title = {Tutorial: Interactive Adaptive Learning}, year = 2024 }
%0 Conference Paper %1 herde2024tutorial %A Herde, Marek %A Pham, Minh Tuan %A Tharwat, Alaa %A Sick, Bernhard %B Workshop on Interactive Adapative Learning (IAL), ECML PKDD %D 2024 %P 1--6 %T Tutorial: Interactive Adaptive Learning %U https://ceur-ws.org/Vol-3770/paper1.pdf %X We summarize the contents of the tutorial we present as a part of the 8th Interactive Adaptive Learning workshop. This workshop is co-located with the ECML-PKDD conference, where it takes place on September 9th, 2024 in Vilnius, Lithuania.

2023[ to top ]

Active Label Refinement for Semantic Segmentation of Satellite Images. Pham, Minh Tuan; Wijesingha, Jayan; Kottke, Daniel; Herde, Marek; Huseljic, Denis; Sick, Bernhard; Wachendorf, Michael; Esch, Thomas. In arXiv e-prints, bl arXiv:2309.06159. 2023.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Remote sensing through semantic segmentation of satellite images contributes to the understanding and utilisation of the earth's surface. For this purpose, semantic segmentation networks are typically trained on large sets of labelled satellite images. However, obtaining expert labels for these images is costly. Therefore, we propose to rely on a low-cost approach, e.g. crowdsourcing or pretrained networks, to label the images in the first step. Since these initial labels are partially erroneous, we use active learning strategies to cost-efficiently refine the labels in the second step. We evaluate the active learning strategies using satellite images of Bengaluru in India, labelled with land cover and land use labels. Our experimental results suggest that an active label refinement to improve the semantic segmentation network's performance is beneficial.
@article{pham2023active, abstract = {Remote sensing through semantic segmentation of satellite images contributes to the understanding and utilisation of the earth's surface. For this purpose, semantic segmentation networks are typically trained on large sets of labelled satellite images. However, obtaining expert labels for these images is costly. Therefore, we propose to rely on a low-cost approach, e.g. crowdsourcing or pretrained networks, to label the images in the first step. Since these initial labels are partially erroneous, we use active learning strategies to cost-efficiently refine the labels in the second step. We evaluate the active learning strategies using satellite images of Bengaluru in India, labelled with land cover and land use labels. Our experimental results suggest that an active label refinement to improve the semantic segmentation network's performance is beneficial.}, author = {Pham, Minh Tuan and Wijesingha, Jayan and Kottke, Daniel and Herde, Marek and Huseljic, Denis and Sick, Bernhard and Wachendorf, Michael and Esch, Thomas}, journal = {arXiv e-prints}, keywords = {itegpub}, pages = {arXiv:2309.06159}, title = {Active Label Refinement for Semantic Segmentation of Satellite Images}, year = 2023 }
%0 Journal Article %1 pham2023active %A Pham, Minh Tuan %A Wijesingha, Jayan %A Kottke, Daniel %A Herde, Marek %A Huseljic, Denis %A Sick, Bernhard %A Wachendorf, Michael %A Esch, Thomas %D 2023 %J arXiv e-prints %P arXiv:2309.06159 %T Active Label Refinement for Semantic Segmentation of Satellite Images %U https://arxiv.org/abs/2309.06159 %X Remote sensing through semantic segmentation of satellite images contributes to the understanding and utilisation of the earth's surface. For this purpose, semantic segmentation networks are typically trained on large sets of labelled satellite images. However, obtaining expert labels for these images is costly. Therefore, we propose to rely on a low-cost approach, e.g. crowdsourcing or pretrained networks, to label the images in the first step. Since these initial labels are partially erroneous, we use active learning strategies to cost-efficiently refine the labels in the second step. We evaluate the active learning strategies using satellite images of Bengaluru in India, labelled with land cover and land use labels. Our experimental results suggest that an active label refinement to improve the semantic segmentation network's performance is beneficial.

2022[ to top ]

Stream-Based Active Learning in Changing Environments under Verification Latency. Pham, Tuan. In Organic Computing -- Doctoral Dissertation Colloquium 2021, S. Tomforde, C. Krupitzer (reds.), bll 152–164. kassel university press, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Labeling data often requires human interaction, which is slow and costly depending on the required expertise. Stream-based active learning reduces the cost of labeling for data stream mining by only querying the labels for instances that improve the classifier the most. However, state-of-the-art stream-based active learning strategies assume that verification latency, i.e., the time between a query and the availability of the queried label, is negligible. In reality, this is usually not the case as the experts who provide such labels are not available all the time, and the labeling process itself requires time. This article investigates the impact of verification latency within a stream-based active learning scenario for changing data streams. We focus on two different types of changes that occur over time, i.e., changes in the number of features and changes in the distribution of instances and/or labels. In particular, we identify challenges that occur due to verification latency and propose ideas to overcome these problems within a stream-based active learning strategy.
@incollection{pham2022stream-based, abstract = {Labeling data often requires human interaction, which is slow and costly depending on the required expertise. Stream-based active learning reduces the cost of labeling for data stream mining by only querying the labels for instances that improve the classifier the most. However, state-of-the-art stream-based active learning strategies assume that verification latency, i.e., the time between a query and the availability of the queried label, is negligible. In reality, this is usually not the case as the experts who provide such labels are not available all the time, and the labeling process itself requires time. This article investigates the impact of verification latency within a stream-based active learning scenario for changing data streams. We focus on two different types of changes that occur over time, i.e., changes in the number of features and changes in the distribution of instances and/or labels. In particular, we identify challenges that occur due to verification latency and propose ideas to overcome these problems within a stream-based active learning strategy.}, author = {Pham, Tuan}, booktitle = {Organic Computing – Doctoral Dissertation Colloquium 2021}, editor = {Tomforde, Sven and Krupitzer, Christian}, keywords = {itegpub}, pages = {152–164}, publisher = {kassel university press}, title = {Stream-Based Active Learning in Changing Environments under Verification Latency}, year = 2022 }
%0 Book Section %1 pham2022stream-based %A Pham, Tuan %B Organic Computing -- Doctoral Dissertation Colloquium 2021 %D 2022 %E Tomforde, Sven %E Krupitzer, Christian %I kassel university press %P 152--164 %T Stream-Based Active Learning in Changing Environments under Verification Latency %X Labeling data often requires human interaction, which is slow and costly depending on the required expertise. Stream-based active learning reduces the cost of labeling for data stream mining by only querying the labels for instances that improve the classifier the most. However, state-of-the-art stream-based active learning strategies assume that verification latency, i.e., the time between a query and the availability of the queried label, is negligible. In reality, this is usually not the case as the experts who provide such labels are not available all the time, and the labeling process itself requires time. This article investigates the impact of verification latency within a stream-based active learning scenario for changing data streams. We focus on two different types of changes that occur over time, i.e., changes in the number of features and changes in the distribution of instances and/or labels. In particular, we identify challenges that occur due to verification latency and propose ideas to overcome these problems within a stream-based active learning strategy.
Stream-based active learning for sliding windows under the influence of verification latency. Pham, Tuan; Kottke, Daniel; Krempl, Georg; Sick, Bernhard. In Machine Learning, 111(6), bll 2011–2036. Springer, 2022.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
Stream-based active learning (AL) strategies minimize the labeling effort by querying labels that improve the classifier's performance the most. So far, these strategies neglect the fact that an oracle or expert requires time to provide a queried label. We show that existing AL methods deteriorate or even fail under the influence of such verification latency. The problem with these methods is that they estimate a label's utility on the currently available labeled data. However, when this label would arrive, some of the current data may have gotten outdated and new labels have arrived. In this article, we propose to simulate the available data at the time when the label would arrive. Therefore, our method Forgetting and Simulating (FS) forgets outdated information and simulates the delayed labels to get more realistic utility estimates. We assume to know the label's arrival date a priori and the classifier's training data to be bounded by a sliding window. Our extensive experiments show that FS improves stream-based AL strategies in settings with both, constant and variable verification latency.
@article{pham2022stream, abstract = {Stream-based active learning (AL) strategies minimize the labeling effort by querying labels that improve the classifier's performance the most. So far, these strategies neglect the fact that an oracle or expert requires time to provide a queried label. We show that existing AL methods deteriorate or even fail under the influence of such verification latency. The problem with these methods is that they estimate a label's utility on the currently available labeled data. However, when this label would arrive, some of the current data may have gotten outdated and new labels have arrived. In this article, we propose to simulate the available data at the time when the label would arrive. Therefore, our method Forgetting and Simulating (FS) forgets outdated information and simulates the delayed labels to get more realistic utility estimates. We assume to know the label's arrival date a priori and the classifier's training data to be bounded by a sliding window. Our extensive experiments show that FS improves stream-based AL strategies in settings with both, constant and variable verification latency.}, author = {Pham, Tuan and Kottke, Daniel and Krempl, Georg and Sick, Bernhard}, journal = {Machine Learning}, keywords = {itegpub}, number = 6, pages = {2011–2036}, publisher = {Springer}, title = {Stream-based active learning for sliding windows under the influence of verification latency}, volume = 111, year = 2022 }
%0 Journal Article %1 pham2022stream %A Pham, Tuan %A Kottke, Daniel %A Krempl, Georg %A Sick, Bernhard %D 2022 %I Springer %J Machine Learning %N 6 %P 2011--2036 %R doi.org/10.1007/s10994-021-06099-z %T Stream-based active learning for sliding windows under the influence of verification latency %V 111 %X Stream-based active learning (AL) strategies minimize the labeling effort by querying labels that improve the classifier's performance the most. So far, these strategies neglect the fact that an oracle or expert requires time to provide a queried label. We show that existing AL methods deteriorate or even fail under the influence of such verification latency. The problem with these methods is that they estimate a label's utility on the currently available labeled data. However, when this label would arrive, some of the current data may have gotten outdated and new labels have arrived. In this article, we propose to simulate the available data at the time when the label would arrive. Therefore, our method Forgetting and Simulating (FS) forgets outdated information and simulates the delayed labels to get more realistic utility estimates. We assume to know the label's arrival date a priori and the classifier's training data to be bounded by a sliding window. Our extensive experiments show that FS improves stream-based AL strategies in settings with both, constant and variable verification latency.

2021[ to top ]

Statistical Analysis of Pairwise Connectivity. Krempl, Georg; Kottke, Daniel; Pham, Tuan. In International Conference on Discovery Science (DS), Lecture Notes in Computer Science, bll 138–148. Springer, 2021.
- [ BibTeX ]
- [ EndNote ]
@inproceedings{krempl2021statistical, author = {Krempl, Georg and Kottke, Daniel and Pham, Tuan}, booktitle = {International Conference on Discovery Science (DS)}, keywords = {itegpub}, pages = {138–148}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, title = {Statistical Analysis of Pairwise Connectivity}, year = 2021 }
%0 Conference Paper %1 krempl2021statistical %A Krempl, Georg %A Kottke, Daniel %A Pham, Tuan %B International Conference on Discovery Science (DS) %D 2021 %I Springer %P 138--148 %R 10.1007/978-3-030-88942-5_11 %T Statistical Analysis of Pairwise Connectivity
scikit-activeml: A Library and Toolbox for Active Learning Algorithms. Kottke, Daniel; Herde, Marek; Minh, Tuan Pham; Benz, Alexander; Mergard, Pascal; Roghman, Atal; Sandrock, Christoph; Sick, Bernhard. In Preprints, bl 2021030194. 2021.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
Machine learning applications often need large amounts of training data to perform well. Whereas unlabeled data can be easily gathered, the labeling process is difficult, time-consuming, or expensive in most applications. Active learning can help solve this problem by querying labels for those data points that will improve the performance the most. Thereby, the goal is that the learning algorithm performs sufficiently well with fewer labels. We provide a library called scikit-activeml that covers the most relevant query strategies and implements tools to work with partially labeled data. It is programmed in Python and builds on top of scikit-learn.
@article{kottke2021scikit, abstract = {Machine learning applications often need large amounts of training data to perform well. Whereas unlabeled data can be easily gathered, the labeling process is difficult, time-consuming, or expensive in most applications. Active learning can help solve this problem by querying labels for those data points that will improve the performance the most. Thereby, the goal is that the learning algorithm performs sufficiently well with fewer labels. We provide a library called scikit-activeml that covers the most relevant query strategies and implements tools to work with partially labeled data. It is programmed in Python and builds on top of scikit-learn.}, author = {Kottke, Daniel and Herde, Marek and Minh, Tuan Pham and Benz, Alexander and Mergard, Pascal and Roghman, Atal and Sandrock, Christoph and Sick, Bernhard}, journal = {Preprints}, keywords = {itegpub}, pages = 2021030194, title = {{scikit-activeml}: {A} Library and Toolbox for Active Learning Algorithms}, year = 2021 }
%0 Journal Article %1 kottke2021scikit %A Kottke, Daniel %A Herde, Marek %A Minh, Tuan Pham %A Benz, Alexander %A Mergard, Pascal %A Roghman, Atal %A Sandrock, Christoph %A Sick, Bernhard %D 2021 %J Preprints %P 2021030194 %T scikit-activeml: A Library and Toolbox for Active Learning Algorithms %U https://www.preprints.org/manuscript/202103.0194/ %X Machine learning applications often need large amounts of training data to perform well. Whereas unlabeled data can be easily gathered, the labeling process is difficult, time-consuming, or expensive in most applications. Active learning can help solve this problem by querying labels for those data points that will improve the performance the most. Thereby, the goal is that the learning algorithm performs sufficiently well with fewer labels. We provide a library called scikit-activeml that covers the most relevant query strategies and implements tools to work with partially labeled data. It is programmed in Python and builds on top of scikit-learn.

2019[ to top ]

Tree Species Classification Based on Hybrid Ensembles of a Convolutional Neural Network (CNN) and Random Forest Classifiers. Knauer, Uwe; Styp von Rekowski, Cornelius; Stecklina, Marianne; Krokotsch, Tilman; Pham Minh, Tuan; Hauffe, Viola; Kilias, David; Ehrhardt, Ina; Sagischewski, Herbert; Chmara, Sergej; Seiffert, Udo. In Remote Sensing, 11(23), bl 2788. MDPI, 2019.
- [ Abstract ]
- [ BibTeX ]
- [ EndNote ]
- [ URL ]
In this paper, we evaluate different popular voting strategies for fusion of classifier results. A convolutional neural network (CNN) and different variants of random forest (RF) classifiers were trained to discriminate between 15 tree species based on airborne hyperspectral imaging data. The spectral data was preprocessed with a multi-class linear discriminant analysis (MCLDA) as a means to reduce dimensionality and to obtain spatial–spectral features. The best individual classifier was a CNN with a classification accuracy of 0.73 +/− 0.086. The classification performance increased to an accuracy of 0.78 +/− 0.053 by using precision weighted voting for a hybrid ensemble of the CNN and two RF classifiers. This voting strategy clearly outperformed majority voting (0.74), accuracy weighted voting (0.75), and presidential voting (0.75).
@article{knauer2019tree, abstract = {In this paper, we evaluate different popular voting strategies for fusion of classifier results. A convolutional neural network (CNN) and different variants of random forest (RF) classifiers were trained to discriminate between 15 tree species based on airborne hyperspectral imaging data. The spectral data was preprocessed with a multi-class linear discriminant analysis (MCLDA) as a means to reduce dimensionality and to obtain spatial–spectral features. The best individual classifier was a CNN with a classification accuracy of 0.73 +/− 0.086. The classification performance increased to an accuracy of 0.78 +/− 0.053 by using precision weighted voting for a hybrid ensemble of the CNN and two RF classifiers. This voting strategy clearly outperformed majority voting (0.74), accuracy weighted voting (0.75), and presidential voting (0.75).}, author = {Knauer, Uwe and Styp von Rekowski, Cornelius and Stecklina, Marianne and Krokotsch, Tilman and Pham Minh, Tuan and Hauffe, Viola and Kilias, David and Ehrhardt, Ina and Sagischewski, Herbert and Chmara, Sergej and Seiffert, Udo}, journal = {Remote Sensing}, keywords = {imported}, number = 23, pages = 2788, publisher = {MDPI}, title = {Tree Species Classification Based on Hybrid Ensembles of a Convolutional Neural Network (CNN) and Random Forest Classifiers}, volume = 11, year = 2019 }
%0 Journal Article %1 knauer2019tree %A Knauer, Uwe %A Styp von Rekowski, Cornelius %A Stecklina, Marianne %A Krokotsch, Tilman %A Pham Minh, Tuan %A Hauffe, Viola %A Kilias, David %A Ehrhardt, Ina %A Sagischewski, Herbert %A Chmara, Sergej %A Seiffert, Udo %D 2019 %I MDPI %J Remote Sensing %N 23 %P 2788 %R 10.3390/rs11232788 %T Tree Species Classification Based on Hybrid Ensembles of a Convolutional Neural Network (CNN) and Random Forest Classifiers %U https://www.mdpi.com/2072-4292/11/23/2788 %V 11 %X In this paper, we evaluate different popular voting strategies for fusion of classifier results. A convolutional neural network (CNN) and different variants of random forest (RF) classifiers were trained to discriminate between 15 tree species based on airborne hyperspectral imaging data. The spectral data was preprocessed with a multi-class linear discriminant analysis (MCLDA) as a means to reduce dimensionality and to obtain spatial–spectral features. The best individual classifier was a CNN with a classification accuracy of 0.73 +/− 0.086. The classification performance increased to an accuracy of 0.78 +/− 0.053 by using precision weighted voting for a hybrid ensemble of the CNN and two RF classifiers. This voting strategy clearly outperformed majority voting (0.74), accuracy weighted voting (0.75), and presidential voting (0.75).