activity
20192021
most citedTraining GANs with Stronger Augmentations via Contrastive Discriminator

8 citations · 12 across the 2 of their papers we have counts for

collaborators

5 papers

cs.LG20218 cited

Training GANs with Stronger Augmentations via Contrastive Discriminator

Jongheon Jeong, Jinwoo Shin

Recent works in Generative Adversarial Networks (GANs) are actively revisiting various data augmentation techniques as an effective way to prevent discriminator overfitting. It is…

cs.LG2020

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

Jihoon Tack, Sangwoo Mo, Jongheon Jeong +1

Novelty detection, i.e., identifying whether a given sample is drawn from outside the training distribution, is essential for reliable machine learning. To this end, there have bee…

cs.LG2020

Consistency Regularization for Certified Robustness of Smoothed Classifiers

Jongheon Jeong, Jinwoo Shin

A recent technique of randomized smoothing has shown that the worst-case (adversarial) -robustness can be transformed into the average-case Gaussian-robustness by "smoothin…

cs.CV2020

M2m: Imbalanced Classification via Major-to-minor Translation

Jaehyung Kim, Jongheon Jeong, Jinwoo Shin

In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this pa…

cs.LG20194 cited

Training CNNs with Selective Allocation of Channels

Jongheon Jeong, Jinwoo Shin

Recent progress in deep convolutional neural networks (CNNs) have enabled a simple paradigm of architecture design: larger models typically achieve better accuracy. Due to this, in…