A meta-framework for multi-label active learning based on deep reinforcement learning

Chen, Shuyue; Wang, Ran; Lü, Jian

doi:10.1016/j.neunet.2023.02.045

Cited by 7 publications

(6 citation statements)

References 81 publications

(78 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. With margin sampling [33], unlabeled samples are sorted in ascending ord on the margin between the model's top two predicted class probabilities. sample 𝑥 , the class probability 𝑝(𝑦 = 𝑗|𝑥 ; 𝑊) is computed for every clas c i )", you should organize the unannotated data samples by sorting them in ascending order according to their cess, we update the labels (𝑦 ) for unlabeled sampl 𝑊, iteratively.…”

Section: Choosing Samples With Uncertaintymentioning

confidence: 99%

“…2. With margin sampling [33], unlabeled samples on the margin between the model's top two p sample 𝑥 , the class probability 𝑝(𝑦 = 𝑗|𝑥 ; 𝑊 c i values, which are calculated as follows: outputs 0. 𝑊 represents the CNN parameters.…”

Section: Choosing Samples With Uncertaintymentioning

confidence: 99%

“…2. With margin sampling [33], unlabeled samples are sorted in ascending order based on the margin between the model's top two predicted class probabilities. For each sample 𝑥 , the class probability 𝑝(𝑦 = 𝑗|𝑥 ; 𝑊) is computed for every class 𝑗. The…”

Section: Choosing Samples With Uncertaintymentioning

confidence: 99%

See 2 more Smart Citations

An Integrated Active Deep Learning Approach for Image Classification from Unlabeled Data with Minimal Supervision

Abdelwahab,

Afifi,

Salama

2023

Electronics

View full text Add to dashboard Cite

The integration of active learning (AL) and deep learning (DL) presents a promising avenue for enhancing the efficiency and performance of deep learning classifiers. This article introduces an approach that seamlessly integrates AL principles into the training process of DL models to build robust image classifiers. The proposed approach employs a unique methodology to select high-confidence unlabeled data points for immediate labeling, reducing the need for human annotation and minimizing annotation costs. Specifically, by combining uncertainty sampling with the pseudo-labeling of confident data, the proposed approach expands the training set efficiently. The proposed approach uses a hybrid active deep learning model that selects the most informative data points that need labeling based on an uncertainty measure. Then, it iteratively retrains a deep neural network classifier on the newly labeled samples. The model achieves high accuracy with fewer manually labeled samples than traditional supervised deep learning by selecting the most informative samples for labeling and retraining in a loop. Experiments on various image classification datasets demonstrate that the proposed model outperforms conventional approaches in terms of classification accuracy and reduced human annotation requirements. The proposed model achieved accuracy of 98.9% and 99.3% for the Cross-Age Celebrity and Caltech Image datasets compared to the conventional approach, which achieved 92.3% and 74.3%, respectively. In summary, this work presents a promising unified active deep learning approach to minimize the human effort in manually labeling data while maximizing classification accuracy by strategically labeling only the most valuable samples for the model.

show abstract

Section: Choosing Samples With Uncertaintymentioning

confidence: 99%

Section: Choosing Samples With Uncertaintymentioning

confidence: 99%

See 1 more Smart Citation

An Integrated Active Deep Learning Approach for Image Classification from Unlabeled Data with Minimal Supervision

Abdelwahab,

Afifi,

Salama

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…In real-world applications, data with unique and correct label is often too costly to obtain (Zhou 2018;Li, Guo, and Zhou 2019;Wang, Yang, and Li 2020;Liu et al 2023;Chen et al 2023). Instead, users with varying knowledge and cultural backgrounds tend to annotate the same image with different labels.…”

Section: Introductionmentioning

confidence: 99%

Controller-Guided Partial Label Consistency Regularization with Unlabeled Data

Wang,

Zhao,

Zhu

et al. 2024

AAAI

View full text Add to dashboard Cite

Partial label learning (PLL) learns from training examples each associated with multiple candidate labels, among which only one is valid. In recent years, benefiting from the strong capability of dealing with ambiguous supervision and the impetus of modern data augmentation methods, consistency regularization-based PLL methods have achieved a series of successes and become mainstream. However, as the partial annotation becomes insufficient, their performances drop significantly. In this paper, we leverage easily accessible unlabeled examples to facilitate the partial label consistency regularization. In addition to a partial supervised loss, our method performs a controller-guided consistency regularization at both the label-level and representation-level with the help of unlabeled data. To minimize the disadvantages of insufficient capabilities of the initial supervised model, we use the controller to estimate the confidence of each current prediction to guide the subsequent consistency regularization. Furthermore, we dynamically adjust the confidence thresholds so that the number of samples of each class participating in consistency regularization remains roughly equal to alleviate the problem of class-imbalance. Experiments show that our method achieves satisfactory performances in more practical situations, and its modules can be applied to existing PLL methods to enhance their capabilities.

show abstract

“…Gao K et al introduced M-L to improve the classification of spectral images, particularly in scenarios with small sample sets [8]. Chen L et al analyzed M-L's over-parameterization in limited supervised data learning, proposing a two-layer structure to address the issue of overfitting [9]. Xu Z's team introduced a general M-L method to adapt to new tasks, simplifying the inequality between various tasks [10].…”

Section: Introductionmentioning

confidence: 99%

Research on the Application Effect of Metalearning Method Based on Prototype Network in Corrective Measures for Member State Audit

Zhu,

2023

J. Comb. Math. Comb. Comput.

View full text Add to dashboard Cite

IMO Member State audits aim to identify non-compliant behavior with the requirements of relevant instruments, enabling the implementation of corrective measures to enhance performance. However, the complexity and diversity of IMO instruments’ requirements result in low evaluation effectiveness and efficiency in current assessment methods of implementation of IMO instruments. To address this challenge, this study proposes a meta-learning model based on prototype networks, focusing on the corrective measures outlined in consolidated audit summary reports approved and issued by the IMO Secretariat. The suggested model conducts meta-learning using small samples, offering a swift and straightforward assessment method. It facilitates the fine classification of corrective measures, providing a way for the consistent and effective assessment of various countriesâ€™ current implementation practices. Empirical results of two strategies demonstrate improved classification accuracy. In comparison with traditional manual evaluation, the proposed method achieves accuracy value 71.61% and 65.78% in two strategies respectively. Furthermore, the model exhibits varying prediction accuracy across different articles and demonstrates robust generalization capabilities, highlighting its practicality.

show abstract

A meta-framework for multi-label active learning based on deep reinforcement learning

Cited by 7 publications

References 81 publications

An Integrated Active Deep Learning Approach for Image Classification from Unlabeled Data with Minimal Supervision

An Integrated Active Deep Learning Approach for Image Classification from Unlabeled Data with Minimal Supervision

Controller-Guided Partial Label Consistency Regularization with Unlabeled Data

Research on the Application Effect of Metalearning Method Based on Prototype Network in Corrective Measures for Member State Audit

Contact Info

Product

Resources

About