检索结果-内蒙古大学图书馆

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is availab.e at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features 38

Not All Diffusion Model Activations Have Been Evaluated as D...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is availab.e at this url. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of a Wideband 1-Bit Metal-Only Reconfigurable Reflectarray Antenna 11

Design of a Wideband 1-Bit Metal-Only Reconfigurable Reflect...

引用

11th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2023 - Proceedings

作者： Li, Xuan Wang, Min Hu, Nan Xie, Wenqing Chen, Shulin Chongqing University of Posts and Telecommunications Postdoctoral Res. Ctr. of Chongqing Key Lab. of Optoelectron. Info. Sensing and Transmiss. Technol. Chongqing400065 China Guilin University of Electronic Technology Guangxi Wireless Broadband Communication and Signal Processing Key Laboratory Guilin541004 China Southeast University State Key Laboratory of Millimeter Waves Nanjing210096 China A-INFO Inc Beijing100084 China Australia

ISBN: (纸本)9798350326277

A 1-bit metal-only reconfigurable reflectarray antenna is proposed in this work. The element of the reflectarray antenna is a 3-D structure composed of a rectangular base, two orthogonal metal plates. By setting two cylindrical slots of different sizes on these two plates, 180° reflected phase difference of two orthogonal linearly polarized waves is obtained. By rotating the proposed element by 90°, the 1 -bit reflected phase can be achieved. Then, a 40 × 40 element reflective aperture spatially fed by a horn antenna is designed and simulated. The beam-scanning of the presented reconfigurable reflectarray antenna can be realized by rotating the elements on the reflective aperture. In simulation, a peak gain of 27.3dBi at 10GHz corresponding to an aperture efficiency of 29.0% are obtained. Furthermore, the maximum gain drop within 60° beam scanning range is 4.0 dB at 10.0GHz while the maximum beam pointing errors is only 1°. These results indicate that this reflectarray antenna has the advantages of high efficiency, wideband and high stability. © 2023 IEEE.

关键词： Beam-scanning high efficiency low cost metal- only reflectarray antenna

来源：评论

学校读者我要写书评

暂无评论

Automatic extraction of lightweight and efficient neural network architecture of heavy convolutional architectures to predict microsatellite instability from hematoxylin and eosin histology in gastric cancer

引用

Neural Computing and Applications 2024年第25期36卷 15295-15321页

作者： Rostami, Habib Ashkpour, Maryam Behzadi-Khormouji, Hamed Mokhtari, Maral Khayati, Armin Keshavarz, Ahmad Talatian Azad, Saeed Tabesh, Yahya Computer Engineering Department Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr75168 Iran Artificial Intelligence and Intelligent Healthcare Lab Artificial Intelligence and Data Mining Research Group Faculty of Intelligent Systems Engineering and Data Science ICT Research Institute Persian Gulf University Bushehr75168 Iran Faculty of New Science and Technologies University of Tehran Tehran Iran Department of Computer Science Imec-IDLab University of Antwerp Sint-Pietersvliet 7 Antwerp2000 Belgium Shahid Faghihi Hospital Shiraz University of Medical Sciences Shiraz Iran Department of Computer Science Engineering and IT School of Electrical and Computer Engineering Shiraz University Shiraz Iran Electrical Engineering Department Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr75168 Iran IoT and Signal Processing Research Group Faculty of Intelligent Systems Engineering and Data Science ICT Research Institute Persian Gulf University Bushehr75168 Iran Department of Mathematical Sciences Sharif University of Technology Tehran Iran

Cancers have emerged as a significant concern due to their impact on public health and society. The examination and interpretation of tissue sections stained with Hematoxylin and Eosin (H&E) play a crucial role in disease assessment, particularly in cases like gastric cancer. Microsatellite instability (MSI) is suggested to contribute to the carcinogenesis of specific gastrointestinal tumors. However, due to the nonspecific morphology observed in H&E-stained tissue sections, MSI determination often requires costly evaluations through various molecular studies and immunohistochemistry methods in specialized molecular pathology lab.ratories. Despite the high cost, international guidelines recommend MSI testing for gastrointestinal cancers. Thus, there is a pressing need for a new diagnostic modality with lower costs and widespread applicability for MSI detection. This study aims to detect MSI directly from H&E histology slides in gastric cancer, providing a cost-effective alternative. The performance of well-known deep convolutional neural networks (DCNNs) and a proposed architecture are compared. Medical image datasets are typically smaller than benchmark datasets like ImageNet, necessitating the use of off-the-shelf DCNN architectures developed for large datasets through techniques such as transfer learning. Designing an architecture proportional to a custom dataset can be tedious and may not yield desirable results. In this work, we propose an automatic method to extract a lightweight and efficient architecture from a given heavy architecture (e.g., well-known off-the-shelf DCNNs) proportional to a specific dataset. To predict MSI instability, we extracted the MicroNet architecture from the Xception network using the proposed method and compared its performance with other well-known architectures. The models were trained using tiles extracted from whole-slide images, and two evaluation strategies, tile-based and whole-slide image (WSI)-based, were employed and comp

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm’s generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is availab.e at https://***/boyuh/AUCSeg. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Audio Visual Speaker Localization from EgoCentric Views

arXiv

引用

arXiv 2023年

作者： Zhao, Jinzheng Xu, Yong Qian, Xinyuan Wang, Wenwu The Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom Tencent AI Lab BellevueWA98004 United States The Department of Computer Science and Technology University of Science and Technology Beijing Beijing100083 China

The use of audio and visual modality for speaker localization has been well studied in the literature by exploiting their complementary characteristics. However, most previous works employ the setting of static sensors mounted at fixed positions. Unlike them, in this work, we explore the ego-centric setting, where the heterogeneous sensors are embodied and could be moving with a human to facilitate speaker localization. Compared to the static scenario, the ego-centric setting is more realistic for smart-home applications e.g., a service robot. However, this also brings new challenges such as blurred images, frequent speaker disappearance from the field of view of the wearer, and occlusions. In this paper, we study egocentric audiovisual speaker Direction of Arrival (DOA) estimation and deal with the challenges mentioned above. Specifically, we propose a transformer-based audio-visual fusion method to estimate the relative DOA of the speaker to the wearer, and design a training strategy to mitigate the problem of the speaker disappearing from the camera's view. We also develop a new dataset for simulating the out-of-view scenarios, by creating a scene with a camera wearer walking around while a speaker is moving at the same time. The experimental results show that our proposed method offers promising performance in this new dataset in terms of tracking accuracy. Finally, we adapt the proposed method for the multi-speaker scenario. Experiments on EasyCom show the effectiveness of the proposed model for multiple speakers in real scenarios, which achieves state-of-the-art results in the sphere active speaker detection task and the wearer activity prediction task. The simulated dataset and related code are availab.e at https://***/KawhiZhao/Egocentric-Audio-Visual-Speaker-Localization. © 2023, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Attention-Based End-to-End Differentiable Particle Filter for Audio Speaker Tracking

TechRxiv

引用

TechRxiv 2023年

作者： Zhao, Jinzheng Xu, Yong Qian, Xinyuan Liu, Haohe Plumbley, Mark D. Wang, Wenwu Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom Tencent AI Lab BellevueWA98004 United States Department of Computer Science and Technology University of Science and Technology Beijing Beijing100083 China

Particle filter (PF) has been widely used in speaker tracking due to its capability of modeling the non-linear process or the non-Gaussian environment. However, particle filter are penalized by many issues. For example, pre-defined handcrafted measurements are often used which can limit the model performance. In addition, the transition and update models are often preset which make PF less flexible to be adapted to different scenarios. To address these issues, we propose an end-to-end differentiable particle filter framework by employing the multi-head attention to model the long-range dependencies. The proposed model employs the self-attention as the learned transition model and the cross-attention as the learned update model. To our knowledge, this is the first proposal of combining particle filter and transformer for speaker tracking, which integrates the measurement extraction, transition and update steps into an end-to-end architecture. Experimental results show that the proposed model achieves superior performance over the recurrent baseline models. © 2023, CC BY.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Recognition of important Korean text structure based on Reinforcement Learning and Self-attention mechanism 2

Recognition of important Korean text structure based on Rein...

引用

2nd International Conference on Artificial Intelligence and Advanced Manufacture, AIAM 2020

作者： Yang, Feiyang Zhao, Yahui Cui, Xu Cui, Rongyi Yanbian University Intelligent Information Processing Lab. Dept. of Computer Science and Technology Yanji133002 China

ISBN: (纸本)9781728199863

Aiming at the problem that the artificial tagging of Korean corpus is too time-consuming and lab.rious, and it is difficult for minority languages to integrate with various resources. We intend to construct an effective Korean structural representation from the perspective of representation learning to improve the effectiveness of subsequent natural language processing tasks. Combining deep reinforcement learning with Self-attention mechanism, we propose a hierarchical self-attention model (Hierarchically Structured Korean, HS-K). By using the Actor-Critic idea in reinforcement learning, the model takes the text classification effect as the lab.l feedback of reinforcement learning, and transforms the text structure division task into the sequence decision task. The experimental results show that the model can identify the important text structure of Korean which closer the manual tagging, and it has a friendly auxiliary effect on Korean informatization and intelligentialize. © 2020 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Course Answering System Based on Error Correction and Trie Tree Language Model

Design and Implementation of a Course Answering System Based...

引用

2020 International Conference on computer Science and Communication technology, ICCSCT 2020

作者： Li, Danyang Zhao, Yahui Luo, Mengjiang Cui, Rongyi Intelligent Information Processing Lab. Dept. of Computer Science and Technology Yanbian University Yanji133002 China

With the rapid growth of network information, the accuracy of input text affects the retrieval results, text proofreading technology emerges as the times require in order to avoid the situation of "wrong answers"caused by wrong questions when searching for information. In the course question answering system, we also need to consider the query speed and efficiency. In order to avoid the trouble of manual proofreading, this paper proposes a system which can automatically correct wrong questions in the professional field of curriculum. Firstly, used the edit distance method for fuzzy matching of error strings;then, used trie tree language model to store data to improve query efficiency. Finally, compared the proofreading effect under different text similarity thresholds, and selected the best value for the experiment. After experimental analysis and comparison, the best result is selected when the text similarity is 0.5, the accuracy rate is 77.91%, the recall rate is 67%, and the F value is 72.04%. Experiments show that the system designed in this paper can effectively correct the wrong text in the field of computer. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Information Reconciliation for Continuous-Variable Quantum Key Distribution Beyond the Devetak-Winter Bound Using Short Blocklength Error Correction Codes

arXiv

引用

arXiv 2024年

作者： Gümüş, Kadir dos Reis Frazão, João Albores-Mejia, Aaron Škorić, Boris Liga, Gabriele Can Gültekin, Yunus Bradley, Thomas Alvarado, Alex Okonkwo, Chigo High Capacity Optical Transmission Laboratory Electro-Optical Communications Group Eindhoven University of Technology Eindhoven5600 MB Netherlands CubiQ Technologies De Groene Loper 5 Eindhoven Netherlands Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven5600 MB Netherlands Information and Communication Theory Lab Signal Processing Group Eindhoven University of Technology 5600MB Netherlands

In this paper we introduce a reconciliation protocol with a two-step error correction scheme using a short blocklength low rate code and a long blocklength high rate code. We show that by using this two-step decoding method it is possible to achieve secret key rates beyond the Devetak-Winter bound. We simulate the protocol using short blocklength low-density parity check code, and show that we can obtain reconciliation efficiencies up to 1.5. Using these high reconciliation efficiencies, it is possible double the achievable distances of CV-QKD systems. © 2024, CC BY.

关键词： Quantum cryptography

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：