Search

Your search keyword '"Lee, Eunji"' showing total 1,887 results
Start Over Author "Lee, Eunji"
1,887 results on '"Lee, Eunji"'

2. Habaek: High-performance water segmentation through dataset expansion and inductive bias optimization

Author

Joo, Hanseon, Lee, Eunji, and Cheon, Minjong

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

Water segmentation is critical to disaster response and water resource management. Authorities may employ high-resolution photography to monitor rivers, lakes, and reservoirs, allowing for more proactive management in agriculture, industry, and conservation. Deep learning has improved flood monitoring by allowing models like CNNs, U-Nets, and transformers to handle large volumes of satellite and aerial data. However, these models usually have significant processing requirements, limiting their usage in real-time applications. This research proposes upgrading the SegFormer model for water segmentation by data augmentation with datasets such as ADE20K and RIWA to boost generalization. We examine how inductive bias affects attention-based models and discover that SegFormer performs better on bigger datasets. To further demonstrate the function of data augmentation, Low-Rank Adaptation (LoRA) is used to lower processing complexity while preserving accuracy. We show that the suggested Habaek model outperforms current models in segmentation, with an Intersection over Union (IoU) ranging from 0.91986 to 0.94397. In terms of F1-score, recall, accuracy, and precision, Habaek performs better than rival models, indicating its potential for real-world applications. This study highlights the need to enhance structures and include datasets for effective water segmentation.

Published
2024

6. Deep-learning-driven end-to-end metalens imaging

Author

Seo, Joonhyuk, Jo, Jaegang, Kim, Joohoon, Kang, Joonho, Kang, Chanik, Moon, Seongwon, Lee, Eunji, Hong, Jehyeong, Rho, Junsuk, and Chung, Haejun

Subjects
Physics - Optics, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Recent advances in metasurface lenses (metalenses) have shown great potential for opening a new era in compact imaging, photography, light detection and ranging (LiDAR), and virtual reality/augmented reality (VR/AR) applications. However, the fundamental trade-off between broadband focusing efficiency and operating bandwidth limits the performance of broadband metalenses, resulting in chromatic aberration, angular aberration, and a relatively low efficiency. In this study, a deep-learning-based image restoration framework is proposed to overcome these limitations and realize end-to-end metalens imaging, thereby achieving aberration-free full-color imaging for mass-produced metalenses with 10-mm diameter. Neural-network-assisted metalens imaging achieved a high resolution comparable to that of the ground truth image., Comment: 17 pages, 7 figures, 1 table

Published
2023

7. Explainable Product Classification for Customs

Author

Lee, Eunji, Kim, Sihyeon, Kim, Sundong, Jung, Soyeon, Kim, Heeja, and Cha, Meeyoung

Subjects
Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Databases, Computer Science - Information Retrieval
Abstract

The task of assigning internationally accepted commodity codes (aka HS codes) to traded goods is a critical function of customs offices. Like court decisions made by judges, this task follows the doctrine of precedent and can be nontrivial even for experienced officers. Together with the Korea Customs Service (KCS), we propose a first-ever explainable decision supporting model that suggests the most likely subheadings (i.e., the first six digits) of the HS code. The model also provides reasoning for its suggestion in the form of a document that is interpretable by customs officers. We evaluated the model using 5,000 cases that recently received a classification request. The results showed that the top-3 suggestions made by our model had an accuracy of 93.9\% when classifying 925 challenging subheadings. A user study with 32 customs experts further confirmed that our algorithmic suggestions accompanied by explainable reasonings, can substantially reduce the time and effort taken by customs officers for classification reviews., Comment: 24 pages, Accepted to ACM Transactions on Intelligent Systems and Technology

Published
2023
Full Text
View/download PDF

12. Accelerated Block-Sparsity-Aware Matrix Reordering for Leveraging Tensor Cores in Sparse Matrix-Multivector Multiplication

Author

Lee, Eunji, Han, Yoonsang, Moon, Gordon Euhyun, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Carretero, Jesus, editor, Shende, Sameer, editor, Garcia-Blas, Javier, editor, Brandic, Ivona, editor, Olcoz, Katzalin, editor, and Schreiber, Martin, editor

Published
2024
Full Text
View/download PDF

15. Post-COVID metabolic enzyme alterations in K18-hACE2 mice exacerbate alcohol-induced liver injury through transcriptional regulation

Author

Park, SiYeong, Lee, Youn Woo, Choi, Seunghoon, Jo, Harin, Kim, NaHyun, Cho, Sumin, Lee, Eunji, Choi, Eun-Bin, Park, Inyoung, Jeon, Young, Noh, Hyuna, Seok, Sang-Hyuk, Oh, Seung Hyun, Choi, Yang-Kyu, Kwon, Ho-Keun, Seo, Jun-Young, Nam, Ki Taek, Park, Jun Won, Choi, Kang-Seuk, Lee, Ho-Young, Yun, Jun-Won, and Seong, Je Kyung

Published
2025
Full Text
View/download PDF

20. 'The Council,' Artist Adelita Husni-Bey and Young Adults Envision the Future Museum

Author

Lee, Eunji J.

Abstract

Artmaking, when used as a form of pedagogy and approached in a socially-conscious manner, has the potential to promote agency and create a democratic learning environment for students. This study examines one such project, "The Council," created by artist Adelita Husni-Bey in collaboration with former Teen Program attendees of the Museum of Modern Art. "The Council" is a collection of large-scale photographs created from a series of workshops in which 13 young adults imagined themselves reshaping the museum's societal role after a major global crisis. The final photographs were exhibited in the museum's main galleries, representing a participatory, socially-engaged artwork produced from a pedagogical process. While there is a prevalence of these types of pedagogy-based artworks, contemporary art literature tends to focus mainly on the artist, disregarding the participants. Therefore, from the stance of an art educator, I examined the learning experiences of the participants as well as the pedagogical framework of the artist. The reviews from the participants were overwhelmingly positive, with many noting a significant increase in their confidence and a greater sense of agency. A liberating experience of collaboration was also stated as a common experience. These outcomes were attributed to the artist's innovative use of multimodal learning and effective facilitation grounded in Francesc Ferrer's philosophy of anarcho-collectivism and integral education, as well as critical pedagogy. This study suggests that creative methodologies can significantly enhance intrinsically motivated learning and emphasises the importance of nurturing the next generation as they envision a more equitable and just society.

Published
2023
Full Text
View/download PDF

25. Classification of Goods Using Text Descriptions With Sentences Retrieval

Author

Lee, Eunji, Kim, Sundong, Kim, Sihyun, Park, Sungwon, Cha, Meeyoung, Jung, Soyeon, Yang, Suyoung, Choi, Yeonsoo, Ji, Sungdae, Song, Minsoo, and Kim, Heeja

Subjects
Computer Science - Artificial Intelligence, Computer Science - Information Retrieval
Abstract

The task of assigning and validating internationally accepted commodity code (HS code) to traded goods is one of the critical functions at the customs office. This decision is crucial to importers and exporters, as it determines the tariff rate. However, similar to court decisions made by judges, the task can be non-trivial even for experienced customs officers. The current paper proposes a deep learning model to assist this seemingly challenging HS code classification. Together with Korea Customs Service, we built a decision model based on KoELECTRA that suggests the most likely heading and subheadings (i.e., the first four and six digits) of the HS code. Evaluation on 129,084 past cases shows that the top-3 suggestions made by our model have an accuracy of 95.5% in classifying 265 subheadings. This promising result implies algorithms may reduce the time and effort taken by customs officers substantially by assisting the HS code classification task.

Published
2021

Catalog

Books, media, physical & digital resources
See catalog results