Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets

Hacohen, Guy; Dekel, Avihu; Weinshall, Daphna

doi:10.48550/arxiv.2202.02794

Cited by 5 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We see that our method outperforms random sampling and other AL baselines by a large margin. We note that in agreement with previous works [6,18], AL strategies that are suited for high budgets do not improve the results of random sampling, while AL strategies that are suited for low budgets do.…”

Section: Resultssupporting

confidence: 91%

“…When the budget contains only a few examples, they will struggle to improve the model's performance, not even reaching the accuracy of the random baseline. Recently, it was shown that uncertainty sampling is inherently unsuited for the low budget regime, which may explain the cold start phenomenon [18]. The low-budget scenario is relevant in many applications, especially those requiring an expert tagger whose time is expensive (e.g a radiologist tagger for tumor detection).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Active Learning Through a Covering Lens

Yehuda¹,

Dekel²,

Hacohen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Deep active learning aims to reduce the annotation cost for deep neural networks, which are notoriously data-hungry. Until recently, deep active learning methods struggled in the low-budget regime, where only a small amount of samples are annotated. The situation has been alleviated by recent advances in self-supervised representation learning methods, which impart the geometry of the data representation with rich information about the points. Taking advantage of this progress, we study the problem of subset selection for annotation through a "covering" lens, proposing ProbCover -a new active learning algorithm for the low budget regime, which seeks to maximize Probability Coverage. We describe a dual way to view our formulation, from which one can derive strategies suitable for the high budget regime of active learning, related to existing methods like Coreset. We conclude with extensive experiments, evaluating ProbCover in the low budget regime. We show that our principled active learning strategy improves the state-of-the-art in the low-budget regime in several image recognition benchmarks. This method is especially beneficial in semi-supervised settings, allowing state-of-the-art semisupervised methods to achieve high accuracy with only a few labels.Preprint. Under review.

show abstract

Section: Resultssupporting

confidence: 91%

Section: Introductionmentioning

confidence: 99%

Active Learning Through a Covering Lens

Yehuda¹,

Dekel²,

Hacohen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition to the above methods, there are also methods that combine active learning and strong data enhancement, such as LADA [46], which not only provides an active learning method that can work under strong data enhancement, but also builds a learnable data enhancement method in turn to improve the effect of data enhancement. They also include Vab-AL [47], which realizes the most valuable sample selection in the case of category imbalance, Revival [48] and Boostmis [49], which combine active learning with semi-supervised learning, and Cluster-Margin [50] and TypiClust [51] which are improved based on the sample size Budget of each selection.…”

Section: Active Learningmentioning

confidence: 99%

An active learning method based on result quality evaluation for printed circuit board computed tomography image segmentation

Song,

Qiao,

Yang

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

Element detection is a key step in non‐destructive testing of printed circuit board (PCB) based on computed tomography (CT). In recent years, some image segmentation methods based on deep learning have shown great potential in the element segmentation task of PCB CT images, and greatly improved the efficiency and accuracy. However, since image segmentation is based on pixel‐level classification, the annotation of training data is difficult and costly. Aiming at this problem, the authors proposed a new active learning method based on the integration of relevant information about segmentation tasks and data variance. In this method, the Result Quality Evaluation Module (RQEM) proposed by us is used to generate task‐related information, and an adversarial network is used to generate the difference information between samples and the initial labelled data. Finally, the two parts of information are fused and used as the standard of data selecting. In the PCB CT image element segmentation task, the authors only need to select 12.7% of the whole training set with their proposed method to make Mean Intersection Over Union (MIOU) reach 79.7, which has reached 95% of the optimal performance of 83.7. The in‐depth analysis also verifies the effectiveness and stability of the authors’ method.

show abstract

“…An important result that connects the paradigm of AL with the available sampling budget is given in [279] who theoretically derive that the best AL strategy crucially depends on the available labeling budget. More precisely, for a high budget, one should query uncertain samples while for a low budget, one should focus on "typical" points where they define the typicality as the inverse of the average squared distance to the nearest neighbors.…”

Section: Different Paradigms For Active Learningmentioning

confidence: 99%

Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey

Wörmann¹,

Bogdoll²,

Bührle³

et al. 2022

Preprint

View full text Add to dashboard Cite

The existence of representative datasets is a prerequisite of many successful artificial intelligence and machine learning models. However, the subsequent application of these models often involves scenarios that are inadequately represented in the data used for training. The reasons for this are manifold and range from time and cost constraints to ethical considerations. As a consequence, the reliable use of these models, especially in safety-critical applications, is a huge challenge. Leveraging additional, already existing sources of knowledge is key to overcome the limitations of purely data-driven approaches, and eventually to increase the generalization capability of these models. Furthermore, predictions that conform with knowledge are crucial for making trustworthy and safe decisions even in underrepresented scenarios. This work provides an overview of existing techniques and methods in the literature that combine data-based models with existing knowledge. The identified approaches are structured according to the categories integration, extraction and conformity. Special attention is given to applications in the field of autonomous driving.Acknowledgement: The research leading to these results is funded by the German Federal Ministry for Economic Affairs and Climate Action within the project "KI Wissen -Entwicklung von Methoden für die Einbindung von Wissen in maschinelles Lernen". The authors would like to thank the consortium for the successful cooperation.

show abstract

Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets

Cited by 5 publications

References 28 publications

Active Learning Through a Covering Lens

Active Learning Through a Covering Lens

An active learning method based on result quality evaluation for printed circuit board computed tomography image segmentation

Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey

Contact Info

Product

Resources

About