Zobrazeno 1 - 10
of 345
pro vyhledávání: '"Kim, KyungSu"'
4D medical images, which represent 3D images with temporal information, are crucial in clinical practice for capturing dynamic changes and monitoring long-term disease progression. However, acquiring 4D medical images poses challenges due to factors
Externí odkaz:
http://arxiv.org/abs/2404.01464
We identify a critical bias in contemporary CLIP-based models, which we denote as single tag bias. This bias manifests as a disproportionate focus on a singular tag (word) while neglecting other pertinent tags, stemming from CLIP's text embeddings th
Externí odkaz:
http://arxiv.org/abs/2404.00384
Weakly-supervised semantic segmentation (WSS) ensures high-quality segmentation with limited data and excels when employed as input seed masks for large-scale vision models such as Segment Anything. However, WSS faces challenges related to minor clas
Externí odkaz:
http://arxiv.org/abs/2404.00380
This study demonstrates the first in-hospital adaptation of a cloud-based AI, similar to ChatGPT, into a secure model for analyzing radiology reports, prioritizing patient data privacy. By employing a unique sentence-level knowledge distillation meth
Externí odkaz:
http://arxiv.org/abs/2402.09358
Weakly-supervised semantic segmentation aims to reduce labeling costs by training semantic segmentation models using weak supervision, such as image-level class labels. However, most approaches struggle to produce accurate localization maps and suffe
Externí odkaz:
http://arxiv.org/abs/2304.09913
The cone-beam computed tomography (CBCT) provides 3D volumetric imaging of a target with low radiation dose and cost compared with conventional computed tomography, and it is widely used in the detection of paranasal sinus disease. However, it lacks
Externí odkaz:
http://arxiv.org/abs/2211.15950
Autor:
Kim, Kyungsu, Park, Minju, Joung, Haesun, Chae, Yunkee, Hong, Yeongbeom, Go, Seonghyeon, Lee, Kyogu
As digital music production has become mainstream, the selection of appropriate virtual instruments plays a crucial role in determining the quality of music. To search the musical instrument samples or virtual instruments that make one's desired soun
Externí odkaz:
http://arxiv.org/abs/2211.07951
Autor:
Kim, Eungbeom, Kim, Jinhee, Oh, Yoori, Kim, Kyungsu, Park, Minju, Sim, Jaeheon, Lee, Jinwoo, Lee, Kyogu
In this paper, we aim to unveil the impact of data augmentation in audio-language multi-modal learning, which has not been explored despite its importance. We explore various augmentation methods at not only train-time but also test-time and find out
Externí odkaz:
http://arxiv.org/abs/2210.17143
Explaining generalizations and preventing over-confident predictions are central goals of studies on the loss landscape of neural networks. Flatness, defined as loss invariability on perturbations of a pre-trained solution, is widely accepted as a pr
Externí odkaz:
http://arxiv.org/abs/2209.15208
Image translation based on a generative adversarial network (GAN-IT) is a promising method for the precise localization of abnormal regions in chest X-ray images (AL-CXR) even without the pixel-level annotation. However, heterogeneous unpaired datase
Externí odkaz:
http://arxiv.org/abs/2207.10324