Combining Active Learning and Data Augmentation for Image Classification

Ma, Yuanming; Lu, Shaoxing; Xu, Erya; Tian, Yu; Zhou, Lijian

doi:10.1145/3422713.3422726

Cited by 4 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Those images were then used as training data in an active learning scenario where a Bayesian neural network identified informative samples to add to the training set. Flip augmentation and Mixup augmentation methods have also been mixed in an active learning scenario with entropy-based query strategy sampling to improve image classification performance [33]. A GAN-based active learning method that seeks to generate high entropy samplings has been proposed in [34], while [35] presented a pool-based active learning algorithm that learns an active learning sampling mechanism in an adversarial manner.…”

Section: Active Learning + Data Augmentationmentioning

confidence: 99%

Exploring Data Augmentation and Active Learning Benefits in Imbalanced Datasets

Moles,

Andres,

Echegaray

et al. 2024

Mathematics

View full text Add to dashboard Cite

Despite the increasing availability of vast amounts of data, the challenge of acquiring labeled data persists. This issue is particularly serious in supervised learning scenarios, where labeled data are essential for model training. In addition, the rapid growth in data required by cutting-edge technologies such as deep learning makes the task of labeling large datasets impractical. Active learning methods offer a powerful solution by iteratively selecting the most informative unlabeled instances, thereby reducing the amount of labeled data required. However, active learning faces some limitations with imbalanced datasets, where majority class over-representation can bias sample selection. To address this, combining active learning with data augmentation techniques emerges as a promising strategy. Nonetheless, the best way to combine these techniques is not yet clear. Our research addresses this question by analyzing the effectiveness of combining both active learning and data augmentation techniques under different scenarios. Moreover, we focus on improving the generalization capabilities for minority classes, which tend to be overshadowed by the improvement seen in majority classes. For this purpose, we generate synthetic data using multiple data augmentation methods and evaluate the results considering two active learning strategies across three imbalanced datasets. Our study shows that data augmentation enhances prediction accuracy for minority classes, with approaches based on CTGANs obtaining improvements of nearly 50% in some cases. Moreover, we show that combining data augmentation techniques with active learning can reduce the amount of real data required.

show abstract

Section: Active Learning + Data Augmentationmentioning

confidence: 99%

Exploring Data Augmentation and Active Learning Benefits in Imbalanced Datasets

Moles,

Andres,

Echegaray

et al. 2024

Mathematics

View full text Add to dashboard Cite

show abstract

“…In [45], the proposed AL method was explicitly designed for image data classifcation, where a deep learning model was implemented as a classifer, but its architecture is not described, the augmentation policies used are unknown and the results reported correspond to single runs of the discussed model. Te remaining AL models found implement data augmentation for NLP applications in [46,47].…”

Section: Data Augmentation In Activementioning

confidence: 99%

Improving Active Learning Performance through the Use of Data Augmentation

Fonseca

Bação

2023

International Journal of Intelligent Systems

View full text Add to dashboard Cite

Active learning (AL) is a well-known technique to optimize data usage in training, through the interactive selection of unlabeled observations, out of a large pool of unlabeled data, to be labeled by a supervisor. Its focus is to find the unlabeled observations that, once labeled, will maximize the informativeness of the training dataset, therefore reducing data-related costs. The literature describes several methods to improve the effectiveness of this process. Nonetheless, there is a paucity of research developed around the application of artificial data sources in AL, especially outside image classification or NLP. This paper proposes a new AL framework, which relies on the effective use of artificial data. It may be used with any classifier, generation mechanism, and data type and can be integrated with multiple other state-of-the-art AL contributions. This combination is expected to increase the ML classifier’s performance and reduce both the supervisor’s involvement and the amount of required labeled data at the expense of a marginal increase in computational time. The proposed method introduces a hyperparameter optimization component to improve the generation of artificial instances during the AL process as well as an uncertainty-based data generation mechanism. We compare the proposed method to the standard framework and an oversampling-based active learning method for more informed data generation in an AL context. The models’ performance was tested using four different classifiers, two AL-specific performance metrics, and three classification performance metrics over 15 different datasets. We demonstrated that the proposed framework, using data augmentation, significantly improved the performance of AL, both in terms of classification performance and data selection efficiency (all the codes and preprocessed data developed for this study are available at https://github.com/joaopfonseca/publications/).

show abstract

Autonomous Outdoor Building Navigation Using a Single Monocular Camera

Seng

McGann

2022

2022 3rd International Conference on Artificial Intelligence, Robotics and Control (AIRC)

View full text Add to dashboard Cite

Combining Active Learning and Data Augmentation for Image Classification

Cited by 4 publications

References 4 publications

Exploring Data Augmentation and Active Learning Benefits in Imbalanced Datasets

Exploring Data Augmentation and Active Learning Benefits in Imbalanced Datasets

Improving Active Learning Performance through the Use of Data Augmentation

Autonomous Outdoor Building Navigation Using a Single Monocular Camera

Contact Info

Product

Resources

About