检索结果-内蒙古大学图书馆

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

Optimal first-order algorithms as a function of inequalities

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 2557-2625页

作者： Chanwoo Park Ernest K. Ryu Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Massachusetts Department of Mathematical Sciences Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea

In this work, we present a novel algorithm design methodology that finds the optimal algorithm as a function of inequalities. Specifically, we restrict convergence analyses of algorithms to use a prespecified subset of inequalities, rather than utilizing all true inequalities, and find the optimal algorithm subject to this restriction. This methodology allows us to design algorithms with certain desired characteristics. As concrete demonstrations of this methodology, we find new state-of-the-art accelerated first-order gradient methods using randomized coordinate updates and backtracking line searches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP

Semantic Token Reweighting for Interpretable and Controllabl...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kim, Eunji Shim, Kyuhong Chang, Simyung Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Qualcomm AI Research an initiative of Qualcomm Technologies Inc. Qualcomm Korea YH Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

ISBN: (纸本)9798891761681

A text encoder within Vision-Language Models (VLMs) like CLIP plays a crucial role in translating textual input into an embedding space shared with images, thereby facilitating the interpretative analysis of vision tasks through natural language. Despite the varying significance of different textual elements within a sentence depending on the context, efforts to account for variation of importance in constructing text embeddings have been lacking. We propose a framework of Semantic Token Reweighting to build Interpretable text embeddings (SToRI), which incorporates controllability as well. SToRI refines the text encoding process in CLIP by differentially weighting semantic elements based on contextual importance, enabling finer control over emphasis responsive to data-driven insights and user preferences. The efficacy of SToRI is demonstrated through comprehensive experiments on few-shot image classification and image retrieval tailored to user preferences. © 2024 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

MarUCOD: Unknown but Concerned Object Detection in Maritime Environments 27th

MarUCOD: Unknown but Concerned Object Detection in Maritim...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Yoon, Hajung Lee, Yoonji Lee, Hwijun Um, Daeho Choi, Hong Seok Choi, Jin Young Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of NexReal Inc. 178 Digital-ro Geumcheon-gu Seoul Korea Republic of

ISBN: (纸本)9783031784460

Detection of unknown but concerned objects such as diverse unknown suspicious objects in the sea area is a critical problem in military defense applications, but the problem is challenging because 1) a pre-trained detector cannot easily detect unknown but concerned objects, 2) it detects too many unconcerned objects such as usual objects in the coastal land area, and 3) we cannot easily establish a well-performing discriminator to divide the detected objects into unknown and known objects, as well as concerned and unconcerned objects because the unknown objects are not available, whereas the concerned and unconcerned objects are not clearly defined. To tackle this challenge, this paper proposes a real-time framework for unknown but concerned object detection in maritime environments by integrating object detection, segmentation, and out-of-distribution (OOD) detection techniques. In our framework, an object detector finds all object-like foregrounds by setting a low threshold and a segmentation deep-learning network filters out unconcerned foregrounds detected in the coastal land area. After that, to discriminate known or unknown objects among concerned objects detected in the sea area, a discriminator performs unsupervised OOD detection using bisecting K-means clustering. To boost the performance of the proposed framework, we apply a pre-processing scheme and a contrastive separation loss for segmentation. The proposed framework achieves a high detection rate of unknown but concerned objects with minimal detection of unconcerned objects (i.e., minimal false positives), surpassing baseline methods and demonstrating potential for enhanced maritime safety and security. The codes are open at https://***/AIX-Coast-Defense-PIL/MarUCOD. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Textual training for the hassle-free removal of unwanted visual data: case studies on OOD and hateful image detection 24

Textual training for the hassle-free removal of unwanted vis...

引用

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

作者： Saehyung Lee Jisoo Mok Sangha Park Yongho Shin Dahuin Jung Sungroh Yoon Department of Electrical and Computer Engineering Seoul National University Qualcomm Korea YH Seoul South Korea School of Computer Science and Engineering Soongsil University Department of Electrical and Computer Engineering and Interdisciplinary Program in Artificial Intelligence Seoul National University

ISBN: (纸本)9798331314385

In our study, we explore methods for detecting unwanted content lurking in visual datasets. We provide a theoretical analysis demonstrating that a model capable of successfully partitioning visual data can be obtained using only textual data. Based on the analysis, we propose Hassle-Free Textual Training (HFTT), a streamlined method capable of acquiring detectors for unwanted visual content, using only synthetic textual data in conjunction with pre-trained vision-language models. HFTT features an innovative objective function that significantly reduces the necessity for human involvement in data annotation. Furthermore, HFTT employs a clever textual data synthesis method, effectively emulating the integration of unknown visual data distribution into the training process at no extra cost. The unique characteristics of HFTT extend its utility beyond traditional out-of-distribution detection, making it applicable to tasks that address more abstract concepts. We complement our analyses with experiments in out-of-distribution detection and hateful image detection. Our codes are available at https://***/Saehyung-Lee/HFTT

关键词：

来源：评论

学校读者我要写书评

暂无评论

ENTROPY IS NOT ENOUGH FOR TEST-TIME ADAPTATION: FROM THE PERSPECTIVE OF DISENTANGLED FACTORS 12

ENTROPY IS NOT ENOUGH FOR TEST-TIME ADAPTATION: FROM THE PER...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Lee, Jonghyun Jung, Dahuin Lee, Saehyung Park, Junsung Shin, Juhyeon Hwang, Uiwon Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of School of Computer Science and Engineering Soongsil University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Division of Digital Healthcare Yonsei University Korea Republic of AIIS ASRI INMC ISRC Seoul National University Korea Republic of

Test-time adaptation (TTA) fine-tunes pre-trained deep neural networks for unseen test data. The primary challenge of TTA is limited access to the entire test dataset during online updates, causing error accumulation. To mitigate it, TTA methods have utilized the model output's entropy as a confidence metric that aims to determine which samples have a lower likelihood of causing error. Through experimental studies, however, we observed the unreliability of entropy as a confidence metric for TTA under biased scenarios and theoretically revealed that it stems from the neglect of the influence of latent disentangled factors of data on predictions. Building upon these findings, we introduce a novel TTA method named Destroy Your Object (DeYO), which leverages a newly proposed confidence metric named Pseudo-Label Probability Difference (PLPD). PLPD quantifies the influence of the shape of an object on prediction by measuring the difference between predictions before and after applying an object-destructive transformation. DeYO consists of sample selection and sample weighting, which employ entropy and PLPD concurrently. For robust adaptation, DeYO prioritizes samples that dominantly incorporate shape information when making predictions. Our extensive experiments demonstrate the consistent superiority of DeYO over baseline methods across various scenarios, including biased and wild. Project page is publicly available at https://***/DeYO/. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

CLeAR: continual learning on algorithmic reasoning for human-like intelligence 23

CLeAR: continual learning on algorithmic reasoning for human...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Bong Gyun Kang HyunGi Kim Dahuin Jung Sungroh Yoon 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

Continual learning (CL) aims to incrementally learn multiple tasks that are presented sequentially. The significance of CL lies not only in the practical importance but also in studying the learning mechanisms of humans who are excellent continual learners. While most research on CL has been done on structured data such as images, there is a lack of research on CL for abstract logical concepts such as counting, sorting, and arithmetic, which humans learn gradually over time in the real world. In this work, for the first time, we introduce novel algorithmic reasoning (AR) methodology for continual tasks of abstract concepts: CLeAR. Our methodology proposes a one-to-many mapping of input distribution to a shared mapping space, which allows the alignment of various tasks of different dimensions and shared semantics. Our tasks of abstract logical concepts, in the form of formal language, can be classified into Chomsky hierarchies based on their difficulty. In this study, we conducted extensive experiments consisting of 15 tasks with various levels of Chomsky hierarchy, ranging from in-hierarchy to inter-hierarchy scenarios. CLeAR not only achieved near zero forgetting but also improved accuracy during following tasks, a phenomenon known as backward transfer, while previous CL methods designed for image classification drastically failed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Impact of Knowledge Distillation for Model Interpretability 40

On the Impact of Knowledge Distillation for Model Interpreta...

引用

40th International Conference on Machine Learning, ICML 2023

作者： Han, Hyeongrok Siwon, Kim Choi, Hyun-Soo Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of ZIOVISION Inc. Chuncheon Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Several recent studies have elucidated why knowledge distillation (KD) improves model performance. However, few have researched the other advantages of KD in addition to its improving model performance. In this study, we have attempted to show that KD enhances the interpretability as well as the accuracy of models. We measured the number of concept detectors identified in network dissection for a quantitative comparison of model interpretability. We attributed the improvement in interpretability to the class-similarity information transferred from the teacher to student models. First, we confirmed the transfer of class-similarity information from the teacher to student model via logit distillation. Then, we analyzed how class-similarity information affects model interpretability in terms of its presence or absence and degree of similarity information. We conducted various quantitative and qualitative experiments and examined the results on different datasets, different KD methods, and according to different measures of interpretability. Our research showed that KD models by large models could be used more reliably in various fields. The code is available at https://***/Rok07/KD_***. © 2023 Proceedings of Machine Learning Research. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Solar Water Pumping: The Role of PLCs and DC-DC Boost Converters in Addressing Water Scarcity

引用

Transportation Research Procedia 2025年 84卷 681-688页

作者： Yumna Mansoor Faizan Zahid Ghulam-E-Mustafa Abro Syed Saad Azhar Summaiya Rajput Ibrahim Akinjobi Aromoye Department of Electrical Engineering Northwestern Polytechnical University Xi’an Shaanxi China Department of Electrical Electronics and Computer Engineering University of Catania Italy Interdisciplinary Research Center for Aviation and Space Exploration King Fahd University of Petroleums and Minerals Saudi Arabia Department of Telecommunication Engineering Mehran University of Engineering and Technology Jamshoro Pakistan Electrical and Electronic Engineering Department Universiti Teknologi PETRONAS Seri Iskandar 32610 Perak Malaysia

This study examines solar water pumping systems with programmable logic controllers (PLCs) to fill a gap in the literature. PLC-based automation can improve these systems’ reliability and efficiency. However, PLC integration with sensors, actuators, and pumps, power consumption optimization, maintenance, and cost-effectiveness prevent their broad implementation. This work analyses two configurations: a DC-DC boost converter-based MPPT solar water pump control scheme and a thorough PLC-based water pumping component research. A well-designed DC-DC boost converter provides motor voltage. This MATLAB-supported method uses solar panels and pumps to solve water scarcity and conserve energy in developing nations.

关键词： Solar Water Pumping programmable Logic Controllers Maximum Power Point Tracking Incremental Conductance DC-DC Boost Converter Photovoltaic (PV) System MATLAB/Simulink

来源：评论

学校读者我要写书评

暂无评论

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORKS 10

STEIN LATENT OPTIMIZATION FOR GENERATIVE ADVERSARIAL NETWORK...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Hwang, Uiwon Kim, Heeseung Jung, Dahuin Jang, Hyemi Lee, Hyungyu Yoon, Sungroh Department of Electrical and Computer Engineering AIIS ASRI INMC ISRC NSI and Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

Generative adversarial networks (GANs) with clustered latent spaces can perform conditional generation in a completely unsupervised manner. In the real world, the salient attributes of unlabeled data can be imbalanced. However, most of existing unsupervised conditional GANs cannot cluster attributes of these data in their latent spaces properly because they assume uniform distributions of the attributes. To address this problem, we theoretically derive Stein latent optimization that provides reparameterizable gradient estimations of the latent distribution parameters assuming a Gaussian mixture prior in a continuous latent space. Structurally, we introduce an encoder network and novel unsupervised conditional contrastive loss to ensure that data generated from a single mixture component represent a single attribute. We confirm that the proposed method, named Stein Latent Optimization for GANs (SLOGAN), successfully learns balanced or imbalanced attributes and achieves state-of-the-art unsupervised conditional generation performance even in the absence of attribute information (e.g., the imbalance ratio). Moreover, we demonstrate that the attributes to be learned can be manipulated using a small amount of probe data. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Generative adversarial networks

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：