Unsupervised active learning with loss prediction

Wan, Chuanbing; Jin, Fusheng; Qiao, Zhuang; Zhang, Weiwei; Yuan, Ye

doi:10.1007/s00521-021-06480-y

Cited by 4 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, active learning can be roughly divided into three categories: uncertainty-based, diversity-based, and hybrid active learning algorithms [24] . Uncertainty-based [25][26] active learning selects data that is difficult to distinguish in the model for labeling, thus achieving the ability to improve the model's performance. Uncertaintybased active learning methods are easy to adapt to various tasks, but they may not perform well in extremely imbalanced sample situations due to considering only the information content of the sample itself.…”

Section: Introductionmentioning

confidence: 99%

Research on classification method of high myopic maculopathy based on retinal fundus images and optimized ALFA-Mix active learning algorithm

Zhu¹,

Wu²,

Zheng³

et al. 2023

Int J Ophthalmol

View full text Add to dashboard Cite

AIM: To conduct a classification study of high myopic maculopathy (HMM) using limited datasets, including tessellated fundus, diffuse chorioretinal atrophy, patchy chorioretinal atrophy, and macular atrophy, and minimize annotation costs, and to optimize the ALFA-Mix active learning algorithm and apply it to HMM classification. METHODS: The optimized ALFA-Mix algorithm (ALFA-Mix+) was compared with five algorithms, including ALFA-Mix. Four models, including ResNet18, were established. Each algorithm was combined with four models for experiments on the HMM dataset. Each experiment consisted of 20 active learning rounds, with 100 images selected per round. The algorithm was evaluated by comparing the number of rounds in which ALFA-Mix+ outperformed other algorithms. Finally, this study employed six models, including EfficientFormer, to classify HMM. The best-performing model among these models was selected as the baseline model and combined with the ALFA-Mix+ algorithm to achieve satisfactory classification results with a small dataset. RESULTS: ALFA-Mix+ outperforms other algorithms with an average superiority of 16.6, 14.75, 16.8, and 16.7 rounds in terms of accuracy, sensitivity, specificity, and Kappa value, respectively. This study conducted experiments on classifying HMM using several advanced deep learning models with a complete training set of 4252 images. The EfficientFormer achieved the best results with an accuracy, sensitivity, specificity, and Kappa value of 0.8821, 0.8334, 0.9693, and 0.8339, respectively. Therefore, by combining ALFA-Mix+ with EfficientFormer, this study achieved results with an accuracy, sensitivity, specificity, and Kappa value of 0.8964, 0.8643, 0.9721, and 0.8537, respectively. CONCLUSION: The ALFA-Mix+ algorithm reduces the required samples without compromising accuracy. Compared to other algorithms, ALFA-Mix+ outperforms in more rounds of experiments. It effectively selects valuable samples compared to other algorithms. In HMM classification, combining ALFA-Mix+ with EfficientFormer enhances model performance, further demonstrating the effectiveness of ALFA-Mix+.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on classification method of high myopic maculopathy based on retinal fundus images and optimized ALFA-Mix active learning algorithm

Zhu¹,

Wu²,

Zheng³

et al. 2023

Int J Ophthalmol

View full text Add to dashboard Cite

show abstract

“…It is important to mention, despite considerable progresses made in the field of pavement crack detection, the deep learning method still requires a large amount of image-based labeling data for model training [8,9]. The labeling work is known to be time-consuming and laborious, and the imbalanced categorical data of the training set would result in a poorly trained model.…”

Section: Introductionmentioning

confidence: 99%

Methodology for Interactive Labeling of Patched Asphalt Pavement Images Based on U-Net Convolutional Neural Network

et al. 2022

View full text Add to dashboard Cite

Image recognition based on deep learning generally demands a huge sample size for training, for which the image labeling becomes inevitably laborious and time-consuming. In the case of evaluating the pavement quality condition, many pavement distress patching images would need manual screening and labeling, meanwhile the subjectivity of the labeling personnel would greatly affect the accuracy of image labeling. In this study, in order for an accurate and efficient recognition of the pavement patching images, an interactive labeling method is proposed based on the U-Net convolutional neural network, using active learning combined with reverse and correction labeling. According to the calculation results in this paper, the sample size required by the interactive labeling is about half of the traditional labeling method for the same recognition precision. Meanwhile, the accuracy of interactive labeling method based on the mean intersection over union (mean_IOU) index is 6% higher than that of the traditional method using the same sample size and training epochs. In addition, the accuracy analysis of the noise and boundary of the prediction results shows that this method eliminates 92% of the noise in the predictions (the proportion of noise is reduced from 13.85% to 1.06%), and the image definition is improved by 14.1% in terms of the boundary gray area ratio. The interactive labeling is considered as a significantly valuable approach, as it reduces the sample size in each epoch of active learning, greatly alleviates the demand for manpower, and improves learning efficiency and accuracy.

show abstract

Active learning for efficient data-driven aerodynamic modeling in spaceplane design

Zhang,

Huang,

Shen

et al. 2024

Physics of Fluids

View full text Add to dashboard Cite

Data-driven surrogate model is extensively applied in the aerodynamics prediction for flight vehicle design. However, for three-dimensional problems, modeling costs hugely in acquiring adequate data. Adaptive and efficient sampling represents a promising approach, so we employ Active Learning (AL) to assess the sampling space. An aerodynamics prediction framework based on the Loss for Active Learning (LLAL) is proposed for capturing the sample insufficient space. The LLAL-based method refines the model by estimating the biases between the ground truths and the predictions as a measure of the high-value samples, then selecting top-K samples for infilling. We first validate our proposed method using an analytical benchmark two-dimensional function, followed by its application to aerodynamics prediction of spaceplane with the number of 60 and the deformation dimensions of 18. Through using both the Latin Hypercube Sampling and LLAL-based methods to infill samples, we observed the R2 of lift-to-drag ratio improves from 0.82 to 0.85. The AL method can enhance the accuracy of models with a limited number of samples, thereby reducing sampling costs and improving the efficiency of aerodynamic design.

show abstract

Unsupervised active learning with loss prediction

Cited by 4 publications

References 21 publications

Research on classification method of high myopic maculopathy based on retinal fundus images and optimized ALFA-Mix active learning algorithm

Research on classification method of high myopic maculopathy based on retinal fundus images and optimized ALFA-Mix active learning algorithm

Methodology for Interactive Labeling of Patched Asphalt Pavement Images Based on U-Net Convolutional Neural Network

Active learning for efficient data-driven aerodynamic modeling in spaceplane design

Contact Info

Product

Resources

About