no code implementations • 18 Oct 2022 • Seung Park, Yong-Goo Shin
For instance, the proposed method improves Frechet inception distance (FID) of StyleGAN2 from 4. 89 to 3. 72 on the FFHQ dataset and from 6. 64 to 5. 57 on the LSUN Bed dataset.
no code implementations • 27 Jan 2022 • Seung Park, Cheol-hwan Yoo, Yong-Goo Shin
For instance, the proposed method improves the FID and IS scores on the tiny-ImageNet dataset from 35. 13 to 27. 90 and 20. 23 to 23. 42, respectively.
no code implementations • 26 Jan 2022 • Yoon-Jae Yeo, Min-Cheol Sagong, Seung Park, Sung-Jea Ko, Yong-Goo Shin
Region-adaptive normalization (RAN) methods have been widely used in the generative adversarial network (GAN)-based image-to-image translation technique.
no code implementations • 30 Dec 2021 • Seung Park, Yong-Goo Shin
To alleviate this problem, this brief introduces a novel generator architecture that produces the image by combining features obtained through two different branches: the main and auxiliary branches.
no code implementations • 30 Nov 2021 • Seung Park, Yong-Goo Shin
This paper introduces a novel convolution method, called generative convolution (GConv), which is simple yet effective for improving the generative adversarial network (GAN) performance.
no code implementations • 19 Jan 2021 • Seung Park, Yoon-Jae Yeo, Yong-Goo Shin
This paper presents a novel convolutional layer, called perturbed convolution (PConv), which focuses on achieving two goals simultaneously: improving the generative adversarial network (GAN) performance and alleviating the memorization problem in which the discriminator memorizes all images from a given dataset as training progresses.
no code implementations • 19 Nov 2019 • Yong-Goo Shin, Yoon-Jae Yeo, Sung-Jea Ko
In adversarial learning, discriminator often fails to guide the generator successfully since it distinguishes between real and generated images using silly or non-robust features.
no code implementations • 18 Nov 2019 • Cheol-hwan Yoo, Seo-won Ji, Yong-Goo Shin, Seung-Wook Kim, Sung-Jea Ko
In this paper, we propose a hierarchically-structured convolutional recurrent neural network (HCRNN) with six branches that estimate the 3D position of the palm and five fingers independently.
no code implementations • 3 Jun 2019 • Min-Cheol Sagong, Yong-Goo Shin, Yoon-Jae Yeo, Seung Park, Sung-Jea Ko
Conditional generative adversarial networks (cGANs) have been widely researched to generate class conditional images using a single generator.
no code implementations • 22 May 2019 • Yong-Goo Shin, Min-Cheol Sagong, Yoon-Jae Yeo, Seung-Wook Kim, Sung-Jea Ko
To address this problem, we propose a novel network architecture called PEPSI: parallel extended-decoder path for semantic inpainting network, which aims at reducing the hardware costs and improving the inpainting performance.
no code implementations • 15 May 2019 • Yong-Goo Shin, Seung Park, Yoon-Jae Yeo, Min-Jae Yoo, Sung-Jea Ko
In the proposed method, the power consumption is constrained by simply reducing the brightness a certain ratio, whereas the perceived visual quality is preserved as much as possible by enhancing the contrast of the image using a convolutional neural network (CNN).