检索结果-内蒙古大学图书馆

44th Annual Conference on European Association for computer Graphics, EUROGRAPHICS 2023

作者： Hwang, Inwoo Kim, Hyeonwoo Lim, Donggeun Park, Inbum Kim, Young Min Seoul National University Department of Electrical and Computer Engineering Korea Republic of Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Korea Republic of

ISBN: (纸本)9783038682097

We present Text2PointCloud, a method to process sparse, noisy point cloud input and generate high-quality stylized output. Given point cloud data, our iterative pipeline stylizes and deforms points guided by a text description and gradually densifies the point cloud. As our framework utilizes the existing resources of image and text embedding, it does not require dedicated 3D datasets with high-quality textures, which are produced by skillful artists or high-resolution colored 3D models. Also, since we represent 3D shapes as a point cloud, we can visualize fine-grained geometric variations with a complex topology such as flowers or fire. To the best of our knowledge, it is the first approach for directly stylizing the uncolored, sparse point cloud input without converting it into a mesh or implicit representation, which might fail to express the original information in the measurements, especially when the object exhibits complex topology. © 2023 Authors.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Zero-shot Denoising for Real-world Images 24

Zero-shot Denoising for Real-world Images

引用

Proceedings of the 2024 7th International Conference on Artificial Intelligence and Pattern Recognition

作者： Hyemi Jang Jooyoung Choi Jaihyun Lew KangHyun Baek Sungroh Yoon Department of Electrical and Computer Engineering Seoul National University Seoul Korea Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Department of Electrical and Computer Engineering and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea

来源：评论

学校读者我要写书评

暂无评论

Unsupervised homography estimation on multimodal image pair via alternating optimization 24

Unsupervised homography estimation on multimodal image pair ...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Sanghyeob Song Jaihyun Lew Hyemi Jang Sungroh Yoon Interdisciplinary Program in Artificial Intelligence Seoul National University and Samsung Electro-Mechanics Interdisciplinary Program in Artificial Intelligence Seoul National University Department of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence Seoul National University and Department of Electrical and Computer Engineering Seoul National University

ISBN: (纸本)9798331314385

Estimating the homography between two images is crucial for mid- or high-level vision tasks, such as image stitching and fusion. However, using supervised learning methods is often challenging or costly due to the difficulty of collecting ground-truth data. In response, unsupervised learning approaches have emerged. Most early methods, though, assume that the given image pairs are from the same camera or have minor lighting differences. Consequently, while these methods perform effectively under such conditions, they generally fail when input image pairs come from different domains, referred to as multimodal image *** address these limitations, we propose AltO, an unsupervised learning framework for estimating homography in multimodal image pairs. Our method employs a two-phase alternating optimization framework, similar to Expectation-Maximization (EM), where one phase reduces the geometry gap and the other addresses the modality gap. To handle these gaps, we use Barlow Twins loss for the modality gap and propose an extended version, Geometry Barlow Twins, for the geometry gap. As a result, we demonstrate that our method, AltO, can be trained on multimodal datasets without any ground-truth data. It not only outperforms other unsupervised methods but is also compatible with various architectures of homography estimators. The source code can be found at: https://***/songsang7/AltO

关键词：

来源：评论

学校读者我要写书评

暂无评论

Grating Coupled Attachment of Optical Fiber Arrays for in situ Photonics Experimentation

Grating Coupled Attachment of Optical Fiber Arrays for in si...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Arnold, Kellen P. Slaby, Joel B. Dattilo, Hannah M. Kaylor, C. Alex Schrimpf, Ronald D. Fleetwood, Daniel M. Ralph, Stephen E. Reed, Robert Weiss, Sharon M. Interdisciplinary Materials Science Program Vanderbilt University 2201 West End Ave NashvilleTN37235 United States School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA30332 United States Department of Electrical and Computer Engineering Vanderbilt University 2201 West End Ave NashvilleTN37235 United States

We report a simple, vacuum-compatible fiber attach process for in situ study of grating-coupled photonic devices. The robustness of this technique is demonstrated on grating-coupled waveguides exposed to multiple X-ra... 详细信息

ISBN: (纸本)9781957171395

关键词： X ray lasers

来源：评论

学校读者我要写书评

暂无评论

Adversarial environment design via regret-guided diffusion models 24

Adversarial environment design via regret-guided diffusion m...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Hojun Chung Junseo Lee Minsoo Kim Dohyeong Kim Songhwai Oh Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University Department of Electrical and Computer Engineering and ASRI Seoul National University Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University and Department of Electrical and Computer Engineering and ASRI Seoul National University

ISBN: (纸本)9798331314385

Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generating a set of training environments tailored to the agent's capabilities. While prior works demonstrate that UED has the potential to learn a robust policy, their performance is constrained by the capabilities of the environment generation. To this end, we propose a novel UED algorithm, adversarial environment design via regret-guided diffusion models (ADD). The proposed method guides the diffusion-based environment generator with the regret of the agent to produce environments that the agent finds challenging but conducive to further improvement. By exploiting the representation power of diffusion models, ADD can directly generate adversarial environments while maintaining the diversity of training environments, enabling the agent to effectively learn a robust policy. Our experimental results demonstrate that the proposed method successfully generates an instructive curriculum of environments, outperforming UED baselines in zero-shot generalization across novel, out-of-distribution environments. Project page: https://***/projects/ADD

关键词：

来源：评论

学校读者我要写书评

暂无评论

Grating Coupled Attachment of Optical Fiber Arrays for in situ Photonics Experimentation

Grating Coupled Attachment of Optical Fiber Arrays for in si...

引用

CLEO: Applications and Technology in CLEO 2024, CLEO: A and T 2024 - Part of Conference on Lasers and Electro-Optics

关键词： Photonic devices

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Chest CT-Scan Anomaly Detection Models Using Principal Component Analysis 25

Evaluation of Chest CT-Scan Anomaly Detection Models Using P...

引用

25th International Arab Conference on Information Technology, ACIT 2024

作者： Alyabrodi, Ala Al-Daja, Shrouq Injadat, MohammadNoor Moubayed, Abdallah Elrashidi, Ali Zarqa University Cyber Security Department Zarqa Jordan Zarqa University Data Science & Ai Department Zarqa Jordan King Fahd University of Petroleum & Minerals Research Center for Intelligent Secure Systems Computer Engineering Department and Interdisciplinary Dhahran Saudi Arabia University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia

ISBN: (纸本)9798331540012

Machine learning-based improvements in anomaly detection, visualization, and segmentation are made possible by the growing digitization of medical imaging, which reduces the workload for medical specialists. Nevertheless, trustworthy labeled data is necessary for supervised machine learning and is sometimes expensive, time-consuming, or impossible to get. Consequently, techniques that need either little labeling (unsupervised methods) or partial labeling (semi-supervised methods) have been used increasingly been used. One approach that can be used to tackle medical imaging tasks like segmentation and classification is anomaly detection, which makes use of both unsupervised and semi-supervised methods. This study investigates the anomaly detection capabilities of deep learning and machine learning models trained on chest CT scans. To adopt this approach, firstly, by evaluating several feature extraction techniques (Principal Component Analysis (PCA), Autoencoder, and variance threshold), PCA achieves the best results on the selected dataset. After that, different machine learning and deep learning models (Isolation Forest, K-means, feed-forward neural networks, and convolutional neural networks) are assessed to detect anomalies using PCA for dimensionality reduction. The experiments show that the NN-Feedforward model with PCA outperformed the other models, also attains remarkably low false alarm rate, demonstrating its effectiveness in reducing false positives and precisely detecting anomalies. © 2024 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Criteria-based Unsupervised Feature Selection Techniques: A Comparative Study Over Chest CT Scan 25

Criteria-based Unsupervised Feature Selection Techniques: A ...

引用

25th International Arab Conference on Information Technology, ACIT 2024

作者： Al-Daja, Shrouq Alyabrodi, Ala' Moubayed, Abdallah Injadat, MohammadNoor Elrashidi, Ali Zarqa University Data Science & Ai Department Zarqa Jordan Zarqa University Cyber Security Department Zarqa Jordan King Fahd University of Petroleum & Minerals Interdisciplinary Research Center for Intelligent Secure Systems Computer Engineering Department Dhahran Saudi Arabia University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia

ISBN: (纸本)9798331540012

Research on classifying chest CT scans as normal or abnormal using machine learning and deep learning has garnered significant attention. To address this, various feature selection (FS) methods are employed to reduce dimensionality and identify key features. This paper evaluates criteria tailored to unsupervised binary datasets, such as feature subsets, redundancy, and diversity, by comparing Mutual Information-Based Methods (MI) with Clustering-Based Feature Selection (Agglomerative Clustering) ones. Additionally, it examines Graph Structure, Spectral Properties, and Quality criteria by comparing Graph-Based Methods with Spectral Feature Selection-be (SPEC). For feature reduction, Agglomerative Clustering may offer a slight advantage due to better handling of diversity and redundancy, though the difference is minimal. If these aspects are crucial, Agglomerative Clustering might be preferred. Conversely, for Graph-Based vs. SPEC, SPEC Method is more suitable for feature reduction due to its coherent feature selection and focus on capturing significant patterns related to medical interventions. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Introducing spectral attention for long-range dependency in time series forecasting 24

Introducing spectral attention for long-range dependency in ...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Bong Gyun Kang Dongjun Lee HyunGi Kim DoHyun Chung Sungroh Yoon Interdisciplinary Program in Artificial Intelligence Seoul National University Department of Electrical and Computer Engineering Seoul National University Department of Future Automotive Mobility Seoul National University Interdisciplinary Program in Artificial Intelligence Seoul National University and Department of Electrical and Computer Engineering Seoul National University

ISBN: (纸本)9798331314385

Sequence modeling faces challenges in capturing long-range dependencies across diverse tasks. Recent linear and transformer-based forecasters have shown superior performance in time series forecasting. However, they are constrained by their inherent inability to effectively address long-range dependencies in time series data, primarily due to using fixed-size inputs for prediction. Furthermore, they typically sacrifice essential temporal correlation among consecutive training samples by shuffling them into mini-batches. To overcome these limitations, we introduce a fast and effective Spectral Attention mechanism, which preserves temporal correlations among samples and facilitates the handling of long-range information while maintaining the base model structure. Spectral Attention preserves long-period trends through a low-pass filter and facilitates gradient to flow between samples. Spectral Attention can be seamlessly integrated into most sequence models, allowing models with fixed-sized look-back windows to capture longrange dependencies over thousands of steps. Through extensive experiments on 11 real-world time series datasets using 7 recent forecasting models, we consistently demonstrate the efficacy of our Spectral Attention mechanism, achieving state-of-the-art results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Diffeomorphic Non-uniform B-spline Flows

arXiv

引用

arXiv 2023年

作者： Hong, Seongmin Chun, Se Young Department of Electrical and Computer Engineering Seoul National University Korea Republic of INMC Interdisciplinary Program in AI Seoul National University Korea Republic of

Normalizing flows have been successfully modeling a complex probability distribution as an invertible transformation of a simple base distribution. However, there are often applications that require more than invertibility. For instance, the computation of energies and forces in physics requires the second derivatives of the transformation to be well-defined and continuous. Smooth normalizing flows employ infinitely differentiable transformation, but with the price of slow non-analytic inverse transforms. In this work, we propose diffeomorphic non-uniform B-spline flows that are at least twice continuously differentiable while bi-Lipschitz continuous, enabling efficient parametrization while retaining analytic inverse transforms based on a sufficient condition for diffeomorphism. Firstly, we investigate the sufficient condition for Ck−2-diffeomorphic non-uniform kth-order B-spline transformations. Then, we derive an analytic inverse transformation of the non-uniform cubic B-spline transformation for neural diffeomorphic non-uniform B-spline flows. Lastly, we performed experiments on solving the force matching problem in Boltzmann generators, demonstrating that our C2-diffeomorphic non-uniform B-spline flows yielded solutions better than previous spline flows and faster than smooth normalizing flows. Our source code is publicly available at https://***/smhongok/Non-uniform-B-spline-Flow. © 2023, CC BY-NC-ND.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：