20 citations · 48 across the 4 of their papers we have counts for
4 papers
Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models
Dogyun Park, Suhyun Kim
Assessing the fidelity and diversity of the generative model is a difficult but important issue for technological advancement. So, recent papers have introduced k-Nearest Neighbor…
NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency
Yujin Kim, Dogyun Park, Dohee Kim +1
We introduce NaturalInversion, a novel model inversion-based method to synthesize images that agrees well with the original data distribution without using real data. In NaturalInv…
GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps
Minsoo Kang, Suhyun Kim
Data augmentation is now an essential part of the image training process, as it effectively prevents overfitting and makes the model more robust against noisy datasets. Recent mixi…
Neuron Merging: Compensating for Pruned Neurons
Woojeong Kim, Suhyun Kim, Mincheol Park +1
Network pruning is widely used to lighten and accelerate neural network models. Structured network pruning discards the whole neuron or filter, leading to accuracy loss. In this wo…