Generative Adversarial Minority Oversampling

Mullick, Sankha Subhra; Datta, Siddhartha; Das, Swagatam

doi:10.1109/iccv.2019.00178

Cited by 156 publications

(75 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the seminal work proposed by Ian Goodfellow et al [1], GANs have been actively researched to generate realistic fake data. For example, many studies have used GANs for imitation [28][29][30]. BAGAN [2] addressed imbalance problems by coupling autoencoders and GANs.…”

Section: Gan-based Methodsmentioning

confidence: 99%

Generative Adversarial Network for Class-Conditional Data Augmentation

2020

View full text Add to dashboard Cite

We propose a novel generative adversarial network for class-conditional data augmentation (i.e., GANDA) to mitigate data imbalance problems in image classification tasks. The proposed GANDA generates minority class data by exploiting majority class information to enhance the classification accuracy of minority classes. For stable GAN training, we introduce a new denoising autoencoder initialization with explicit class conditioning in the latent space, which enables the generation of definite samples. The generated samples are visually realistic and have a high resolution. Experimental results demonstrate that the proposed GANDA can considerably improve classification accuracy, especially when datasets are highly imbalanced on standard benchmark datasets (i.e., MNIST and CelebA). Our generated samples can be easily used to train conventional classifiers to enhance their classification accuracy.

show abstract

Section: Gan-based Methodsmentioning

confidence: 99%

Generative Adversarial Network for Class-Conditional Data Augmentation

2020

View full text Add to dashboard Cite

show abstract

“…Traditional oversampling techniques are usually employed after the feature extraction step in training data [63]. However, as DL algorithms utilize end-to-end feature extraction and classification, incorporating oversampling techniques with DL models would require costly parameter tuning [63], [64]. Furthermore, these techniques can work for low dimension tabular data but not for high-dimensional image data [65] [66].…”

Section: B Data Balancing Using Generative Adversarial Network (Gans)mentioning

confidence: 99%

Intelligent Pneumonia Identification From Chest X-Rays: A Systematic Literature Review

2021

View full text Add to dashboard Cite

Chest radiography is a significant diagnostic tool used to detect diseases afflicting the chest. The automatic detection techniques associated with computer vision are being adopted in medical imaging research. Over the last decade, several remarkable advancements have been made in the field of medical diagnostics with the application of deep learning techniques. Various automated systems have been proposed for the rapid detection of pneumonia from chest X-rays. Although several algorithms are currently available for pneumonia detection, a detailed review summarizing the literature and offering guidelines for medical practitioners is lacking. This study will help practitioners to select the most effective and efficient methods from a real-time perspective, review the available datasets, and understand the results obtained in this domain. It will also present an overview of the literature on intelligent pneumonia identification from chest X-rays. The usability, goodness factors, and computational complexities of the algorithms employed for intelligent pneumonia identification are analyzed. Additionally, this study discusses the quality, usability, and size of the available chest X-ray datasets and techniques for coping with unbalanced datasets. A detailed comparison of the available studies reveals that the majority of the applied datasets are highly unbalanced and limited, providing unreliable results and rendering methods that are unsuitable for large-scale use. Large-scale balanced datasets can be obtained via smart techniques, such as generative adversarial networks. Current literature has indicated that deep learning-based algorithms achieve the best results for pneumonia classification with an accuracy of 98.7%, a sensitivity of 0.99, and a specificity of 0.98. The higher accuracy offered by deep-learning algorithms in addition to their appropriate class balancing techniques serves as a good reference for further research.

show abstract

“…Therefore, different data re-sampling techniques have been proposed by the researchers to balance the training data distribution. This is done either by over-sampling the minority class ( Mullick et al, 2019 ) or under-sampling the majority class ( Drummond et al, 2003 ). However, a recent study has shown that even models trained with balanced datasets amplify bias ( Wang et al, 2019 ).…”

Section: Related Workmentioning

confidence: 99%

Subgroup Invariant Perturbation for Unbiased Pre-Trained Model Prediction

et al. 2021

View full text Add to dashboard Cite

Modern deep learning systems have achieved unparalleled success and several applications have significantly benefited due to these technological advancements. However, these systems have also shown vulnerabilities with strong implications on the fairness and trustability of such systems. Among these vulnerabilities, bias has been an Achilles’ heel problem. Many applications such as face recognition and language translation have shown high levels of bias in the systems towards particular demographic sub-groups. Unbalanced representation of these sub-groups in the training data is one of the primary reasons of biased behavior. To address this important challenge, we propose a two-fold contribution: a bias estimation metric termed as Precise Subgroup Equivalence to jointly measure the bias in model prediction and the overall model performance. Secondly, we propose a novel bias mitigation algorithm which is inspired from adversarial perturbation and uses the PSE metric. The mitigation algorithm learns a single uniform perturbation termed as Subgroup Invariant Perturbation which is added to the input dataset to generate a transformed dataset. The transformed dataset, when given as input to the pre-trained model reduces the bias in model prediction. Multiple experiments performed on four publicly available face datasets showcase the effectiveness of the proposed algorithm for race and gender prediction.

show abstract

Generative Adversarial Minority Oversampling

Cited by 156 publications

References 38 publications

Generative Adversarial Network for Class-Conditional Data Augmentation

Generative Adversarial Network for Class-Conditional Data Augmentation

Intelligent Pneumonia Identification From Chest X-Rays: A Systematic Literature Review

Subgroup Invariant Perturbation for Unbiased Pre-Trained Model Prediction

Contact Info

Product

Resources

About