检索结果-内蒙古大学图书馆

Guest Editorial: Special Issue on Technology Trends in Control, Robotics and Systems - For the 30th Anniversary of the Institute of Control, Robotics and Systems -

学校读者我要写书评

暂无评论

Journal of Institute of Control, Robotics and Systems 2024年第4期30卷 295-295页

作者： Ko, Nak Yong Kang, Taesam Song, Jin Woo Lim, Myo Taeg Jo, Kang-Hyun Department of Electronic Engineering Interdisciplinary Program in IT-Bio Convergence System Chosun University Korea Republic of Department of Mechanical and Aerospace Engineering Konkuk University Korea Republic of Department of Intelligent Mechatronics Engineering Sejong University Korea Republic of School of Electrical Engineering Korea University Korea Republic of Department of Electrical Electronic and Computer Engineering University of Ulsan Korea Republic of

Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kim, Eunji Kim, Siwon Park, Minjun Entezari, Rahim Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Stability AI United Kingdom AIIS ASRI INMC ISRC Seoul National University Korea Republic of

Recent advancements in text-to-image models, such as Stable Diffusion, show significant demographic biases. Existing debiasing techniques rely heavily on additional training, which imposes high computational costs and risks of compromising core image generation functionality. This hinders them from being widely adopted to real-world applications. In this paper, we explore Stable Diffusion’s overlooked potential to reduce bias without requiring additional training. Through our analysis, we uncover that initial noises associated with minority attributes form "minority regions" rather than scattered. We view these "minority regions" as opportunities in SD to reduce bias. To unlock the potential, we propose a novel de-biasing method called ‘weak guidance,’ carefully designed to guide a random noise to the minority regions without compromising semantic integrity. Through analysis and experiments on various versions of SD, we demonstrate that our proposed approach effectively reduces bias without additional training, achieving both efficiency and preservation of core image generation functionality. © 2024, CC BY-NC-SA.

关键词： Digital elevation model

DEAL: Decoupled Classifier with Adaptive Linear Modulation for Group Robust Early Diagnosis of MCI to AD Conversion

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lee, Donggyu Park, Juhyeon Moon, Taesup The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of The Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of The Department of Electrical and Computer Engineering Automation and Systems Research Institute Institute of New Media and Communications Interdisciplinary Program in Artificial Intelligence Artificial Intelligent Institute Seoul National University Seoul08826 Korea Republic of

While deep learning-based Alzheimer's disease (AD) diagnosis has recently made significant advancements, particularly in predicting the conversion of mild cognitive impairment (MCI) to AD based on MRI images, there remains a critical gap in research regarding the group robustness of the diagnosis. Although numerous studies pointed out that deep learning-based classifiers may exhibit poor performance in certain groups by relying on unimportant attributes, this issue has been largely overlooked in the early diagnosis of MCI to AD conversion. In this paper, we present the first comprehensive investigation of the group robustness in the early diagnosis of MCI to AD conversion using MRI images, focusing on disparities in accuracy between groups, specifically sMCI and pMCI individuals divided by age. Our experiments reveal that standard classifiers consistently underperform for certain groups across different architectures, highlighting the need for more tailored approaches. To address this, we propose a novel method, dubbed DEAL (DEcoupled classifier with Adaptive Linear modulation), comprising two key components: (1) a linear modulation of features from the penultimate layer, incorporating easily obtainable age and cognitive indicative tabular features, and (2) a decoupled classifier that provides more tailored decision boundaries for each group, further improving performance. Through extensive experiments and evaluations across different architectures, we demonstrate the efficacy of DEAL in improving the group robustness of the MCI to AD conversion prediction. © 2024, CC BY-NC-SA.

关键词：

NCU-IISR/AS-GIS: Using BERTScore and Snippet Score to Improve the Performance of Pretrained Language Model in BioASQ 10b Phase B

学校读者我要写书评

暂无评论

NCU-IISR/AS-GIS: Using BERTScore and Snippet Score to Improv...

2022 Conference and Labs of the Evaluation Forum, CLEF 2022

作者： Ting, Hao-Hsuan Zhang, Yu Han, Jen-Chieh Tsai, Richard Tzong-Han Interdisciplinary Program of Electrical Engineering and Computer Science National Central University Taiwan Department of Computer Science and Information Engineering National Central University Taiwan IoX Center National Taiwan University Taiwan Research Center for Humanities and Social Sciences Academia Sinica Taiwan

This paper presents our system for the BioASQ10b Phase B task. For ideal answers, we used the fine-tuned BioBERT model on the MNLI dataset to construct sentence embeddings and combined it with BERTScore to select sentences from the provided Snippets as answers. For the exact answers, we also used the BioBERT model and used the snippet scores generated from the ideal answer selection model to predict the exact answers for factoid and list questions. The exact answers of our fifth test batch ranked second place. In addition, the ideal answers we submitted achieved first place in the ROUGE score in all test batches from batch second to fifth. © 2022 Copyright for this paper by its authors.

关键词： Computational linguistics

Adaptive GLCM sampling for transformer-based COVID-19 detection on CT

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jung, Okchul Kang, Dong Un Kim, Gwanghyun Chun, Se Young Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in AI Seoul National University Korea Republic of

The world has suffered from COVID-19 (SARS-CoV-2) for the last two years, causing much damage and change in people’s daily lives. Thus, automated detection of COVID-19 utilizing deep learning on chest computed tomography (CT) scans became promising, which helps correct diagnosis efficiently. Recently, transformer-based COVID-19 detection method on CT is proposed to utilize 3D information in CT volume. However, its sampling method for selecting slices is not optimal. To leverage rich 3D information in CT volume, we propose a transformer-based COVID-19 detection using a novel data curation and adaptive sampling method using gray level co-occurrence matrices (GLCM). To train the model which consists of CNN layer, followed by transformer architecture, we first executed data curation based on lung segmentation and utilized the entropy of GLCM value of every slice in CT volumes to select important slices for the prediction. The experimental results show that the proposed method improve the detection performance with large margin without much difficult modification to the model. © 2022, CC BY.

关键词： COVID-19

Membership Privacy-preserving GAN 33

学校读者我要写书评

暂无评论

Membership Privacy-preserving GAN

33rd British Machine Vision Conference Proceedings, BMVC 2022

作者： Ha, Heonseok Hwang, Uiwon Jang, Jaehee Bae, Ho Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Department of Cyber Security Ewha Womans University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

A membership inference attack (MIA) identifies if an instance was included in the victim model's train dataset. Without an appropriate defense mechanism, MIA can result in serious privacy breaches. Although several methods have been proposed to protect membership privacy in discriminative models, research into generative adversarial networks (GANs), remains insufficient despite their vulnerability to MIAs. In this study, we propose a membership privacy-preserving GAN (MP-GAN), which plays an additional adversarial game for membership privacy between an auxiliary membership inference network M and a GAN. M seeks to find out whether an instance belongs to the reference or train dataset, whereas the generator and discriminator of the GAN attempt to deceive M. Our theoretical analysis results demonstrate that the MP-GAN improves membership privacy by not learning sample-specific features. We perform extensive empirical evaluations to show that the MP-GAN can successfully defend against MIAs under advantageous scenarios to the attacker (for example, white-box access to networks and small training dataset size). Furthermore, we demonstrate that the MP-GAN has several advantages over other privacy-preserving GAN training techniques. © 2022. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.

关键词： Generative adversarial networks

On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Park, Sangha Mok, Jisoo Jung, Dahuin Lee, Saehyung Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

Successful detection of Out-of-Distribution (OoD) data is becoming increasingly important to ensure safe deployment of neural networks. One of the main challenges in OoD detection is that neural networks output overconfident predictions on OoD data, make it difficult to determine OoD-ness of data solely based on their predictions. Outlier exposure addresses this issue by introducing an additional loss that encourages low-confidence predictions on OoD data during training. While outlier exposure has shown promising potential in improving OoD detection performance, all previous studies on outlier exposure have been limited to utilizing visual outliers. Drawing inspiration from the recent advancements in vision-language pre-training, this paper venture out to the uncharted territory of textual outlier exposure. First, we uncover the benefits of using textual outliers by replacing real or virtual outliers in the image-domain with textual equivalents. Then, we propose various ways of generating preferable textual outliers. Our extensive experiments demonstrate that generated textual outliers achieve competitive performance on large-scale OoD and hard OoD benchmarks. Furthermore, we conduct empirical analyses of textual outliers to provide primary criteria for designing advantageous textual outliers: near-distribution, descriptiveness, and inclusion of visual semantics. © 2023, CC BY-NC-SA.

关键词： Forecasting

Development of LiFx/Al2O3/ITO Multilayer Antireflection Coatings for Reflectance Reduction in Silicon Heterojunction Solar Cells

学校读者我要写书评

暂无评论

Physica Status Solidi (A) Applications and Materials Science 2025年第0期

作者： aida, Maha Nur Khokhar, Muhammad Quddamah Yousuf, Hasnain Chu, Mengmeng Rahman, Rafi Ur Alamgeer, Khan Bae, Junhan Jang, Seokjin Yi, Junsin Department of Future Energy Engineering Sungkyunkwan University Gyeonggi-Do Suwon16419 Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Gyeonggi-Do Suwon16419 Korea Republic of Interdisciplinary Program in Photovoltaic System Engineering Sungkyunkwan University Gyeonggi-Do Suwon16419 Korea Republic of

This study focuses on the optimization of antireflection coatings (ARCs) to enhance the performance of silicon heterojunction (SHJ) solar cells. SHJ solar cells face a significant challenge in achieving their theoretical efficiency limits due to light reflection at the air–cell interface. This reflection reduces photon absorption, which limits photocurrent generation and hinders the widespread adoption of SHJ technology. To address this, the optimization of ARCs using single, double, and triple-layer designs with a graded refractive index material as the active layer is investigated. The optimization process is simulated by calculating the layer thicknesses using OPAL2 software and validated through experimental deposition. The results demonstrate that a triple-layer ARC structure consisting of 80/50/95 nm of indium tin oxide (ITO), aluminum oxide (Al2O3), and lithium fluoride (LiFx) significantly improves SHJ performance. This configuration leads to a 1.04 mA cm−2 increase in short-circuit current density (Jsc), reaching 39.85 mA cm−2, and an efficiency of 21.62%, compared to a single-layer ARC. This study presents a promising solution to improve SHJ solar cell efficiency by reducing reflection losses and optimizing optical properties, contributing to the advancement of SHJ technology and facilitating the development of more efficient and cost-effective photovoltaic systems for sustainable energy transition. © 2025 Wiley-VCH GmbH.

关键词： Antireflection coatings

The KIND Dataset: A Social Collaboration Approach for Nuanced Dialect Data Collection 18

学校读者我要写书评

暂无评论

The KIND Dataset: A Social Collaboration Approach for Nuance...

18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024 - Student Research Workshop, SRW 2024

作者： Yamani, Asma Z. Alziyady, Raghad AlYami, Reem Albelali, Salma A. Abouhagar, Leina Almulhim, Jawharah Alsulami, Amjad Alfarraj, Motaz Al-Zaidy, Rabeah Department of Information and Computer Science King Fahd University of Petroleum & Minerals Saudi Arabia Center for Integrative Petroleum Research CIPR King Fahd University of Petroleum & Minerals Saudi Arabia Department of Electrical Engineering King Fahd University of Petroleum & Minerals Saudi Arabia SDAIA-KFUPM Joint Research Center for AI King Fahd University of Petroleum & Minerals Saudi Arabia Preparatory Year Program King Fahd University of Petroleum & Minerals Saudi Arabia Department of Computer Science Imam Abdulrahman Bin Faisal University Saudi Arabia Saudi Data & AI Authority Saudi Arabia

ISBN: (纸本)9798891760905

Nuanced dialects are a linguistic variant that pose several challenges for NLP models and techniques. One of the main challenges is the limited amount of datasets to enable extensive research and experimentation. We propose an approach for efficiently collecting nuanced dialectal datasets that are not only of high quality, but are versatile enough to be multipurpose as well. To test our approach we collect the KIND corpus, which is a collection of fine-grained Arabic dialect data. The data is short texts, and unlike many nuanced dialectal datasets, it is curated manually through social collaboration efforts as opposed to being crawled from social media. The collaborative approach is incentivized through educational gamification and competitions for which the community itself benefits from the open source dataset. Our approach aims to achieve: (1) coverage of dialects from under-represented groups and fine-grained dialectal varieties, (2) provide aligned parallel corpora for translation between Modern Standard Arabic (MSA) and multiple dialects to enable translation and comparison studies, (3) promote innovative approaches for nuanced dialect data collection. We explain the steps for the competition as well as the resulting datasets and the competing data collection systems. The KIND dataset is shared with the research community. © 2024 Association for Computational Linguistics.

关键词： Data acquisition