From: The use of generative adversarial networks to alleviate class imbalance in tabular data: a survey
Rank | Paper | Count |
---|---|---|
1 | Generative adversarial networks | 31 |
2 | Unsupervised representation learning with deep convolutional generative adversarial networks | 16 |
3 | Smote: Synthetic minority oversampling technique | 15 |
4 | Conditional generative adversarial nets | 11 |
5 | Deep Residual Learning for ImageRecognition | 9 |
6 | Deep generative image models using a laplacian pyramid of adversarial networks | 8 |
6 | Bagan: Data augmentation with balancing gan | 8 |
6 | Improved techniques for training GANs | 8 |
9 | Learning deep representation for imbalanced classification | 7 |
9 | Learning multiple layers of features from tiny images | 7 |
9 | Unpaired imagetoimage translation using cycleconsistent adversarial networks | 7 |
9 | Conditional image synthesis with auxiliary classifier GANs. | 7 |
9 | BorderlineSMOTE: A new oversampling method in imbalanced data sets learning | 7 |
9 | ADASYN: Adaptive synthetic sampling approach for imbalanced learning | 7 |
15 | AutoEncoding VariationalBayes | 6 |
15 | Data augmentation generative adversarial networks | 6 |
15 | Effective data generation for imbalanced learning using Conditional Generative Adversarial Networks | 6 |
15 | ImageNet classification with deep convolutionalneural networks | 6 |
15 | Learning from imbalanced data | 6 |
20 | Wasserstein gan | 5 |