no code implementations • 27 Feb 2024 • Mincheol Park, DongJin Kim, Cheonjun Park, Yuna Park, Gyeong Eun Gong, Won Woo Ro, Suhyun Kim
Channel pruning is widely accepted to accelerate modern convolutional neural networks (CNNs).
no code implementations • 24 Jan 2024 • Minsoo Kang, Minkoo Kang, Suhyun Kim
Deep learning has made significant advances in computer vision, particularly in image classification tasks.
1 code implementation • ICCV 2023 • Dogyun Park, Suhyun Kim
Assessing the fidelity and diversity of the generative model is a difficult but important issue for technological advancement.
1 code implementation • 29 Jun 2023 • Yujin Kim, Dogyun Park, Dohee Kim, Suhyun Kim
We introduce NaturalInversion, a novel model inversion-based method to synthesize images that agrees well with the original data distribution without using real data.
1 code implementation • 29 Jun 2023 • Minsoo Kang, Suhyun Kim
From this motivation, we propose a novel saliency-aware mixup method, GuidedMixup, which aims to retain the salient regions in mixup images with low computational overhead.
1 code implementation • ICLR 2023 • Minjae Kim, Sangyoon Yu, Suhyun Kim, Soo-Mook Moon
Federated learning is for training a global model without collecting private local data from clients.
1 code implementation • NeurIPS 2020 • Woojeong Kim, Suhyun Kim, Mincheol Park, Geonseok Jeon
Network pruning is widely used to lighten and accelerate neural network models.
no code implementations • 14 Jul 2020 • Mincheol Park, Woojeong Kim, Suhyun Kim
Even though norm-based filter pruning methods are widely accepted, it is questionable whether the "smaller-norm-less-important" criterion is optimal in determining filters to prune.