1 code implementation • 1 Mar 2021 • Mahsa Paknezhad, Cuong Phuc Ngo, Amadeus Aristo Winarto, Alistair Cheong, Chuen Yang Beh, Jiayang Wu, Hwee Kuan Lee
We found that models trained using our framework, as well as other regularization methods and adversarial training support our hypothesis of data sparsity and that models trained with these methods learn to have decision boundaries more similar to the aforementioned ideal decision boundary.
1 code implementation • 2 Apr 2019 • Cuong Phuc Ngo, Amadeus Aristo Winarto, Connie Kou Khor Li, Sojeong Park, Farhan Akram, Hwee Kuan Lee
However, the traditional GAN loss is not directly aligned with the anomaly detection objective: it encourages the distribution of the generated samples to overlap with the real data and so the resulting discriminator has been found to be ineffective as an anomaly detector.