Dual generative adversarial active learning

Guo, Jifeng; Pang, Zhiqi; Bai, Miaoyuan; Xie, Peijiao; Chen, Yu

doi:10.1007/s10489-020-02121-4

Cited by 12 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dual Generative Adversarial Active Learning (DGAAL) is a novel active learning method that combines pool-based and synthesis-based approaches to reduce annotation costs while maintaining good model performance [ 21 ]. It uses two Generative Adversarial Networks (GANs) consisting of a generator and two discriminators.…”

Section: Related Workmentioning

confidence: 99%

RETRACTED ARTICLE: Robust adversarial uncertainty quantification for deep learning fine-tuning

Ahmed

Lin

2023

J Supercomput

View full text Add to dashboard Cite

This paper proposes a deep learning model that is robust and capable of handling highly uncertain inputs. The model is divided into three phases: creating a dataset, creating a neural network based on the dataset, and retraining the neural network to handle unpredictable inputs. The model utilizes entropy values and a non-dominant sorting algorithm to identify the candidate with the highest entropy value from the dataset. This is followed by merging the training set with adversarial samples, where a mini-batch of the merged dataset is used to update the dense network parameters. This method can improve the performance of machine learning models, categorization of radiographic images, risk of misdiagnosis in medical imaging, and accuracy of medical diagnoses. To evaluate the efficacy of the proposed model, two datasets, MNIST and COVID, were used with pixel values and without transfer learning. The results showed an increase of accuracy from 0.85 to 0.88 for MNIST and from 0.83 to 0.85 for COVID, which suggests that the model successfully classified images from both datasets without using transfer learning techniques.

show abstract

Section: Related Workmentioning

confidence: 99%

RETRACTED ARTICLE: Robust adversarial uncertainty quantification for deep learning fine-tuning

Ahmed

Lin

2023

J Supercomput

View full text Add to dashboard Cite

show abstract

“…Moreover, promising research directions have been explored to extend DAL algorithms regarding the integration of different annotation granularity, abundant unlabeled data and related supervision setting into active learning pipeline, including multi-label [19], multi-view [20], multi-instance [10], multi-instance multi-label (M2AL) [21], multi-view multi-instance multi-label (M3AL) [22], and unsupervised [23], [14] AL schemes. Among them, more attention has been paid to address two aspects: the automatic design of selection samples strategy [24] and the alleviation of various problems, namely data-related problems such as confidence and insufficient labeled sample, model-related problems such as generalization ability, and domain-specific problems such as domain shift, cold-start problem and class imbalance.…”

Section: A Active Learning For Deep Architecturesmentioning

confidence: 99%

A Cost-effective Deep Active Learning for Object Detection in Automated Driving Systems

Khebbache,

Bitam,

Mellouk

2023

IJCDS

View full text Add to dashboard Cite

In Automated Driving Systems (ADS), the function of detecting objects on the road assists vehicle traffic and improves road safety. Deep Active Learning (DAL) is an advanced training method suitable for building robust Convolutional Neural Network (CNN)-based on road object detection models. This method automatically selects and manually labels training samples that are significantly less noisy, non-redundant and more useful. Depending on the complexity of detection task and the characteristics of urban scenes, the batch selection in the conventional batch mode DAL can suffer from the impact of the correlation between frame labels and batch size as well as variable labeling costs. This paper introduces a novel cost-effective-based training approach suitable for CNN-based on-road object detector, where frames labeling and batch size are considered in the sample selection process. We propose a batch sampling strategy that leverages the model prediction uncertainty along with dynamic programming to alleviate the selection batch size issue. Additionally, we investigate the effects of classification uncertainty, regression uncertainty and batch size during sample selection. Our approach was extensively validated on the Caltech Pedestrian dataset to fine-tune a pre-trained Tiny-YOLOv3 for performing pedestrian detection task. Results showed that our approach, compared to basic methods, can build robust detection model that keeps the detection error less than 57%, saving up 50% of the labeling effort and alleviating batch size dependency.

show abstract

“…Thus the superiority of BLPM is verified. We compared the performance of IEAAL with the current mainstream methods, including Random, Monte Carlo dropout (MC dropout) [52], Core-set [38], LLAL [19], VAAL [39], SRAAL [18], ARAL [25] and DGAAL [53]. Figure 7a shows the performance on CIFAR-100.…”

Section: Ablation Studymentioning

confidence: 99%

Independency‐enhancing adversarial active learning

Guo

Pang

Bai

et al. 2022

IET Image Processing

Self Cite

View full text Add to dashboard Cite

The core idea of active learning is to obtain higher model performance with less annotation cost. This paper proposes an independency‐enhancing adversarial active learning method. Independency‐enhancing adversarial active learning is different from the previous methods and pays more attention to sample independence. Specifically, it is believed that the informativeness of a group of samples is related to sample independence rather than the simple sum of the informativeness of each sample in the group. Therefore, an independent sample selection module based on hierarchical clustering is designed to ensure sample independence. An adversarial approach is used to learn the feature representation of a sample and use the predicted loss value to label the state of the sample. Finally, samples are selected according to the uncertainty of the samples, the diversity of the samples and the independence of the samples. The experimental results on four datasets (CIFAR‐100, Caltech‐101, Cityscapes and BDD100K) demonstrate the effectiveness and superiority of independency‐enhancing adversarial active learning.

show abstract

Dual generative adversarial active learning

Cited by 12 publications

References 34 publications

RETRACTED ARTICLE: Robust adversarial uncertainty quantification for deep learning fine-tuning

RETRACTED ARTICLE: Robust adversarial uncertainty quantification for deep learning fine-tuning

A Cost-effective Deep Active Learning for Object Detection in Automated Driving Systems

Independency‐enhancing adversarial active learning

Contact Info

Product

Resources

About