Classification of acoustical signals by combining active learning strategies with semi-supervised learning schemes

Karlos, Stamatis; Aridas, Christos K.; Kanas, Vasileios G.; Kotsiantis, Sotiris

doi:10.1007/s00521-021-05749-6

Cited by 11 publications

(5 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this pool can also be used for semi-supervised learning (SSL), where the objective is to learn jointly from labeled and unlabeled samples. The combination of SSL and AL has been used successfully in many contexts, such as speech understanding [9,20], image classification [13,27,28,31], and pedestrian detection [30]. Some recent works have also studied active learning methods with the integration of SSL for segmentation, but their scope is limited only to special cases like subsampled driving datasets [29] or low labeling budget [27], both cases with only single-sample acquisition methods.…”

Section: Semi-supervised Active Learningmentioning

confidence: 99%

Best Practices in Active Learning for Semantic Segmentation

Mittal,

Niemeijer,

Schäfer

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Active learning is particularly of interest for semantic segmentation, where annotations are costly. Previous academic studies focused on datasets that are already very diverse and where the model is trained in a supervised manner with a large annotation budget. In contrast, data collected in many driving scenarios is highly redundant, and most medical applications are subject to very constrained annotation budgets. This work investigates the various types of existing active learning methods for semantic segmentation under diverse conditions across three dimensions -data distribution w.r.t. different redundancy levels, integration of semi-supervised learning, and different labeling budgets. We find that these three underlying factors are decisive for the selection of the best active learning approach. As an outcome of our study, we provide a comprehensive usage guide to obtain the best performance for each case. It is the first systematic study that investigates these dimensions covering a wide range of settings including more than 3K model training runs. In this work, we also propose an exemplary evaluation task for driving scenarios, where data has high redundancy, to showcase the practical implications of our research findings.

show abstract

Section: Semi-supervised Active Learningmentioning

confidence: 99%

Best Practices in Active Learning for Semantic Segmentation

Mittal,

Niemeijer,

Schäfer

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Recently, a combination of SSL and AL has gained attention in the community due to advances in SSL methods. It has been applied to various tasks like speech understanding [10,20], pedestrian detection [31], and image classification [14,28,29,32]. Some AL methods [37] for semantic segmentation used unlabeled and labeled data to measure the sample's representativeness.…”

Section: Related Workmentioning

confidence: 99%

Revisiting Deep Active Learning for Semantic Segmentation

Mittal¹,

Niemeijer²,

Schäfer³

et al. 2023

Preprint

View full text Add to dashboard Cite

Active learning automatically selects samples for annotation from a data pool to achieve maximum performance with minimum annotation cost. This is particularly critical for semantic segmentation, where annotations are costly. In this work, we show in the context of semantic segmentation that the data distribution is decisive for the performance of the various active learning objectives proposed in the literature. Particularly, redundancy in the data, as it appears in most driving scenarios and video datasets, plays a large role. We demonstrate that the integration of semisupervised learning with active learning can improve performance when the two objectives are aligned. Our experimental study shows that current active learning benchmarks for segmentation in driving scenarios are not realistic since they operate on data that is already curated for maximum diversity. Accordingly, we propose a more realistic evaluation scheme in which the value of active learning becomes clearly visible, both by itself and in combination with semisupervised learning.

show abstract

“…Semi-supervised learning uses both, that combines a small amount of labeled data with a large amount of unlabeled data during training, and at EDM the majority of the proposed methods that operate using labeled and unlabeled data kinds of these data are oriented toward exploiting only one category of these algorithms, without combining their strategies. Since the most popular of them regarding the classification task are Active and Semi-supervised Learning approaches, Karlos et al [15] design a framework that combines both of them, trying to fuse their advantages during the main core of the learning process.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Predicting Students at Risk of Dropout in Technical Course Using LMS Logs

2022

View full text Add to dashboard Cite

Educational data mining is a process that aims at discovering patterns that provide insight into teaching and learning processes. This work uses Machine Learning techniques to create a student performance prediction model, using academic data and records from a Learning Management System, that correlates with success or failure in completing the course. Six algorithms were employed, with models trained at three different stages of their two-year course completion. We tested the models with records of 394 students from 3 courses. Random Forest provided the best results with 84.47% on the F1 score in our experiments, followed by Decision Tree obtaining similar results in the first subjects. We also employ clustering techniques and find different behavior groups with a strong correlation to performance. This work contributes to predicting students at risk of dropping out, offers insight into understanding student behavior, and provides a support mechanism for academic managers to take corrective and preventive actions on this problem.

show abstract

Classification of acoustical signals by combining active learning strategies with semi-supervised learning schemes

Cited by 11 publications

References 59 publications

Best Practices in Active Learning for Semantic Segmentation

Best Practices in Active Learning for Semantic Segmentation

Revisiting Deep Active Learning for Semantic Segmentation

Predicting Students at Risk of Dropout in Technical Course Using LMS Logs

Contact Info

Product

Resources

About