检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Jung, Dahuin Lee, Dongjin Hong, Sunwon Jang, Hyemi Bae, Ho Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of DeepBrain AI Inc. Korea Republic of Department of Cyber Security Ewha Womans University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul08826 Korea Republic of

The aim of continual learning is to learn new tasks continuously (i.e., plasticity) without forgetting previously learned knowledge from old tasks (i.e., stability). In the scenario of online continual learning, wherein data comes strictly in a streaming manner, the plasticity of online continual learning is more vulnerable than offline continual learning because the training signal that can be obtained from a single data point is limited. To overcome the stability-plasticity dilemma in online continual learning, we propose an online continual learning framework named multi-scale feature adaptation network (MuFAN) that utilizes a richer context encoding extracted from different levels of a pre-trained network. Additionally, we introduce a novel structure-wise distillation loss and replace the commonly used batch normalization layer with a newly proposed stability-plasticity normalization module to train MuFAN that simultaneously maintains high plasticity and stability. MuFAN outperforms other state-of-the-art continual learning methods on the SVHN, CIFAR100, miniImageNet, and CORe50 datasets. Extensive experiments and ablation studies validate the significance and scalability of each proposed component: 1) multi-scale feature maps from a pre-trained encoder, 2) the structure-wise distillation loss, and 3) the stability-plasticity normalization module in MuFAN. Code is publicly available at https://***/whitesnowdrop/MuFAN. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Stability

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

Conference on Lasers and Electro-Optics (CLEO)

作者： Kellen P. Arnold Joel B. Slaby Hannah M. Dattilo C. Alex Kaylor Ronald D. Schrimpf Daniel M. Fleetwood Stephen E. Ralph Robert Reed Sharon M. Weiss Interdisciplinary Materials Science Program Vanderbilt University Nashville TN USA School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA Department of Electrical and Computer Engineering Vanderbilt University Nashville TN USA

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)9798350369311

关键词： Optical fibers Radiation effects X-ray lasers Waveguide lasers Fiber gratings Robustness Optical fiber devices Arrayed waveguide gratings Photonics Optical arrays

来源：评论

学校读者我要写书评

暂无评论

Photonic Crystals with Split Ring Unit Cells for Subwavelength Light Confinement

Photonic Crystals with Split Ring Unit Cells for Subwaveleng...

引用

CLEO: Science and Innovations, S and I 2022

作者： Arnold, Kellen P. Halimi, Sami I. Allen, Joshua A. Hu, Shuren Weiss, Sharon M. Interdisciplinary Materials Science Program Vanderbilt University NashvilleTN37235 United States Department of Electrical Engineering and Computer Science Vanderbilt University NashvilleTN37235 United States

We report a split ring photonic crystal that demonstrates an order of magnitude larger peak energy density compared to traditional photonic crystals. The split ring offers highly focused optical energy in an accessibl...

ISBN: (纸本)9781557528209

关键词：

来源：评论

学校读者我要写书评

暂无评论

Text2Scene: Text-driven Indoor Scene Stylization with Part-Aware Details

Text2Scene: Text-driven Indoor Scene Stylization with Part-A...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Inwoo Hwang Hyeonwoo Kim Young Min Kim Department of Electrical and Computer Engineering Seoul National University Interdisciplinary Program in Artificial Intelligence and INMC Seoul National University

We propose Text2Scene, a method to automatically create realistic textures for virtual scenes composed of multiple objects. Guided by a reference image and text descriptions, our pipeline adds detailed texture on labeled 3D geometries in the room such that the generated colors respect the hierarchical structure or semantic parts that are often composed of similar materials. Instead of applying flat stylization on the entire scene at a single step, we obtain weak semantic cues from geometric segmentation, which are further clarified by assigning initial colors to segmented parts. Then we add texture details for individual objects such that their projections on image space exhibit feature embedding aligned with the embedding of the input. The decomposition makes the entire pipeline tractable to a moderate amount of computation resources and memory. As our framework utilizes the existing resources of image and text embedding, it does not require dedicated datasets with high-quality textures designed by skillful artists. To the best of our knowledge, it is the first practical and scalable approach that can create detailed and realistic textures of the desired style that maintain structural context for scenes with multiple objects.

关键词：

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

arXiv

引用

arXiv 2024年

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

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 © 2024, CC BY-NC-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage

arXiv

引用

arXiv 2024年

作者： Lee, Saehyung Yoon, Seunghyun Bui, Trung Shi, Jing Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Adobe Research Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

Multimodal large language models (MLLMs) excel at generating highly detailed captions but often produce hallucinations. Our analysis reveals that existing hallucination detection methods struggle with detailed captions. We attribute this to the increasing reliance of MLLMs on their generated text, rather than the input image, as the sequence length grows. To address this issue, we propose a multiagent approach that leverages LLM-MLLM collaboration to correct given captions. Additionally, we introduce an evaluation framework and a benchmark dataset to facilitate the systematic analysis of detailed captions. Our experiments demonstrate that our proposed evaluation method better aligns with human judgments of factuality than existing metrics and that existing approaches to improve the MLLM factuality may fall short in hyper-detailed image captioning tasks. In contrast, our proposed method significantly enhances the factual accuracy of captions, even improving those generated by GPT-4V. Finally, we highlight a limitation of VQA-centric benchmarking by demonstrating that an MLLM’s performance on VQA benchmarks may not correlate with its ability to generate detailed image captions. © 2024, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Safe CoR: A Dual-Expert Approach to Integrating Imitation Learning and Safe Reinforcement Learning Using Constraint Rewards

Safe CoR: A Dual-Expert Approach to Integrating Imitation Le...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Hyeokjin Kwon Gunmin Lee Junseo Lee Songhwai Oh Interdisciplinary Program in Artificial Intelligence and ASRI Seoul National University Seoul Korea Department of Electrical and Computer Engineering and ASRI Seoul National University Seoul Korea

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In the realm of autonomous agents, ensuring safety and reliability in complex and dynamic environments remains a paramount challenge. Safe reinforcement learning addresses these concerns by introducing safety constraints, but still faces challenges in navigating intricate environments such as complex driving situations. To overcome these challenges, we present the safe constraint reward (Safe CoR) framework, a novel method that utilizes two types of expert demonstrations—reward expert demonstrations focusing on performance optimization and safe expert demonstrations prioritizing safety. By exploiting a constraint reward (CoR), our framework guides the agent to balance performance goals of reward sum with safety constraints. We test the proposed framework in diverse environments, including the safety gym, metadrive, and the real-world Jackal platform. Our proposed framework improves algorithm performance by 39% and reduces constraint violations by 88% on the real-world Jackal platform, highlighting its effectiveness. Through this innovative approach, we expect significant advancements in real-world performance, leading to transformative effects in the realm of safe and reliable autonomous agents.

关键词： Navigation Imitation learning Focusing Reinforcement learning Autonomous agents Safety Reliability Optimization Intelligent robots Faces

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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：

来源：评论

学校读者我要写书评

暂无评论

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

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

引用

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

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：