Zobrazeno 1 - 10
of 534
pro vyhledávání: '"Kim, Hyunsu"'
Group Equivariant CNNs (G-CNNs) have shown promising efficacy in various tasks, owing to their ability to capture hierarchical features in an equivariant manner. However, their equivariance is fixed to the symmetry of the whole group, limiting adapta
Externí odkaz:
http://arxiv.org/abs/2407.04271
Publikováno v:
ICLR 2024
Deep Ensemble (DE) approach is a straightforward technique used to enhance the performance of deep neural networks by training them from different initial points, converging towards various local optima. However, a limitation of this methodology lies
Externí odkaz:
http://arxiv.org/abs/2404.15814
We present the Groupwise Diffusion Model (GDM), which divides data into multiple groups and diffuses one group at one time interval in the forward diffusion process. GDM generates data sequentially from one group at one time interval, leading to seve
Externí odkaz:
http://arxiv.org/abs/2310.01400
Multivariate time series data for real-world applications typically contain a significant amount of missing values. The dominant approach for classification with such missing values is to impute them heuristically with specific values (zero, mean, va
Externí odkaz:
http://arxiv.org/abs/2308.06738
Autor:
Kim, Sunwoo, Jang, Wooseok, Kim, Hyunsu, Kim, Junho, Choi, Yunjey, Kim, Seungryong, Lee, Gayeong
Recent text-driven image editing in diffusion models has shown remarkable success. However, the existing methods assume that the user's description sufficiently grounds the contexts in the source image, such as objects, background, style, and their r
Externí odkaz:
http://arxiv.org/abs/2306.02717
Datasets often have their intrinsic symmetries, and particular deep-learning models called equivariant or invariant models have been developed to exploit these symmetries. However, if some or all of these symmetries are only approximate, which freque
Externí odkaz:
http://arxiv.org/abs/2306.00356
Autor:
Kim, Doyeon, Ko, Eunji, Kim, Hyunsu, Kim, Yunji, Kim, Junho, Min, Dongchan, Kim, Junmo, Hwang, Sung Ju
Portrait stylization, which translates a real human face image into an artistically stylized image, has attracted considerable interest and many prior works have shown impressive quality in recent years. However, despite their remarkable performances
Externí odkaz:
http://arxiv.org/abs/2305.19135
With the advantages of fast inference and human-friendly flexible manipulation, image-agnostic style manipulation via text guidance enables new applications that were not previously available. The state-of-the-art text-guided image-agnostic manipulat
Externí odkaz:
http://arxiv.org/abs/2302.13331
Image blending aims to combine multiple images seamlessly. It remains challenging for existing 2D-based methods, especially when input images are misaligned due to differences in 3D camera poses and object shapes. To tackle these issues, we propose a
Externí odkaz:
http://arxiv.org/abs/2302.06608
Autor:
Shin, Minjung, Seo, Yunji, Bae, Jeongmin, Choi, Young Sun, Kim, Hyunsu, Byun, Hyeran, Uh, Youngjung
3D-aware GANs aim to synthesize realistic 3D scenes such that they can be rendered in arbitrary perspectives to produce images. Although previous methods produce realistic images, they suffer from unstable training or degenerate solutions where the 3
Externí odkaz:
http://arxiv.org/abs/2301.09091