8 citations
- Adobe Systems (United States)US2 papers
- Hanbat National UniversityKR2 papers
- Kootenay Association for Science & TechnologyCA1 paper
- Korea Advanced Institute of Science and TechnologyKR1 paper
- Lunit (South Korea)KR1 paper
- Palo Alto UniversityUS1 paper
- Seoul National University HospitalKR1 paper
- Stanford UniversityUS1 paper
- Yonsei UniversityKR1 paper
6 papers
Studying the Effects of Self-Attention for Medical Image Analysis
Adrit Rao, Jongchan Park, Sanghyun Woo +2
When the trained physician interprets medical images, they understand the clinical importance of visual features. By applying cognitive attention, they apply greater focus onto cli…
Exploiting Features with Split-and-Share Module
Jaemin Lee, Minseok Seo, Jongchan Park +1
Deep convolutional neural networks (CNNs) have shown state-of-the-art performances in various computer vision tasks. Advances on CNN architectures have focused mainly on designing…
Polygonal Point Set Tracking
Gunhee Nam, Miran Heo, Seoung Wug Oh +2
In this paper, we propose a novel learning-based polygonal point set tracking method. Compared to existing video object segmentation~(VOS) methods that propagate pixel-wise object…
Learning Visual Context by Comparison
Minchul Kim, Jongchan Park, Seil Na +2
Finding diseases from an X-ray image is an important yet highly challenging task. Current methods for solving this task exploit various characteristics of the chest X-ray image, bu…
Sequential Feature Filtering Classifier
Minseok Seo, Jaemin Lee, Jongchan Park +1
We propose Sequential Feature Filtering Classifier (FFC), a simple but effective classifier for convolutional neural networks (CNNs). With sequential LayerNorm and ReLU, FFC zeroes…
PseudoEdgeNet: Nuclei Segmentation only with Point Annotations
Inwan Yoo, Donggeun Yoo, Kyunghyun Paeng
Nuclei segmentation is one of the important tasks for whole slide image analysis in digital pathology. With the drastic advance of deep learning, recent deep networks have demonstr…