检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Zhiyong Yang Qianqian Xu Zitai Wang Sicong Li Boyu Han Shilong Bao Xiaochun Cao Qingming Huang School of Computer Science and Tech. University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and 2Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and BDKM University of Chinese Academy of Sciences

This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can be broken down hierarchically into global and local levels. The global ones reflect a broad range of diversity, while the local ones typically arise from milder changes, often focused on a particular neighbor. Traditional methods predominantly use a Mixture-of-Expert (MoE) approach, targeting a few fixed test label distributions that exhibit substantial global variations. However, the local variations are left unconsidered. To address this issue, we propose a new MoE strategy, DirMixE, which assigns experts to different Dirichlet meta-distributions of the label distribution, each targeting a specific aspect of local variations. Additionally, the diversity among these Dirichlet meta-distributions inherently captures global variations. This dual-level approach also leads to a more stable objective function, allowing us to sample different test distributions better to quantify the mean and variance of performance outcomes. Theoretically, we show that our proposed objective benefits from enhanced generalization by virtue of the variance-based regularization. Comprehensive experiments across multiple benchmarks confirm the effectiveness of DirMixE. The code is available at https://***/scongl/DirMixE.

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 available 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

Leveraging Semisupervised Hierarchical Stacking Temporal Convolutional Network for Anomaly Detection in IoT Communication

Leveraging Semisupervised Hierarchical Stacking Temporal Con...

引用

作者： Cheng, Yongliang Xu, Yan Zhong, Hong Liu, Yi Anhui Engineering Laboratory of IoT Security Technologies Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Shenzhen Key Laboratory of Intelligent Media and Speech Peking University Shenzhen Institute Shenzhen China

The rapid development of the Internet of Things (IoT) accumulates a large number of communication records, which are utilized for anomaly detection in IoT communication. However, only a small part of these records can be labeled, which increases the difficulty in anomaly detection. This article proposes a semisupervised hierarchical stacking temporal convolutional network (HS-TCN), which is the first semisupervised model for anomaly detection in IoT communication, and it can train unlabeled data based on a small number of labeled data. Furthermore, HS-TCN fully considers the features of streaming data in IoT communication and can weed out uncertain records. Finally, the experimental results demonstrate that HS-TCN promotes the performance of anomaly detection and attains better efficiency. © 2014 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Some 3-designs invariant under 2.PΣL(2,49)

arXiv

引用

arXiv 2024年

作者： Shi, Minjia Liu, Ruowen Solé, Patrick The Key Laboratory of Intelligent Computing Signal Processing Ministry of Education School of Mathematical Sciences Anhui University Hefei230601 China State Key Laboratory of integrated Service Networks Xidian University Xi’an710071 China Aix Marseille Univ CNRS I2M Marseilles France

We construct a ternary [49,25,7] code from the row span of a Jacobsthal matrix. It is equivalent to a Generalized Quadratic Residue (GQR) code in the sense of van Lint and MacWilliams (1978). These codes are the abelian generalizations of the quadratic residue (QR) codes which are cyclic. The union of the [50,25,8] extension of the said code and its dual supports a 3-(50,14,1248) design. The automorphism group of the latter design is a double cover of the permutation part of the automorphism group of the [50,25,8] code, which is isomorphic to PΣL(2, 49). Other weights in this code, other GQR codes, and other QR codes yield other 3-designs by the same process. A simple group action argument is provided to explain this behaviour of isodual *** Codes 94 B15, 05 B05 Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SVFormer: Semi-supervised Video Transformer for Action Recognition

SVFormer: Semi-supervised Video Transformer for Action Recog...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhen Xing Qi Dai Han Hu Jingjing Chen Zuxuan Wu Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Microsoft Research Asia

Semi-supervised action recognition is a challenging but critical task due to the high cost of video annotations. Existing approaches mainly use convolutional neural networks, yet current revolutionary vision transformer models have been less explored. In this paper, we investigate the use of transformer models under the SSL setting for action recognition. To this end, we introduce SVFormer, which adopts a steady pseudo-labeling framework (i.e., EMA-Teacher) to cope with unlabeled video samples. While a wide range of data augmentations have been shown effective for semi-supervised image classification, they generally produce limited results for video recognition. We therefore introduce a novel augmentation strategy, Tube Token-Mix, tailored for video data where video clips are mixed via a mask with consistent masked tokens over the temporal axis. In addition, we propose a temporal warping augmentation to cover the complex temporal variation in videos, which stretches selected frames to various temporal durations in the clip. Extensive experiments on three datasets Kinetics-400, UCF-101, and HMDB-51 verify the advantage of SVFormer. In particular, SVFormer outperforms the state-of-the-art by 31.5% with fewer training epochs under the 1% labeling rate of Kinetics-400. Our method can hopefully serve as a strong benchmark and encourage future search on semi-supervised action recognition with Transformer networks. Code is released at https://***/ChenHsing/SVFormer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Colors display with spatial light modulator based on inf-wavelength metal grating

Colors display with spatial light modulator based on inf-wav...

引用

2020 Applied Optics and Photonics China: Optoelectronics and Nanophotonics;and Quantum Information Technology, AOPC 2020

作者： Tao, Bo Wang, GuiZhu Wei, Sui Shen, Chuan Xu, ZhangMing Key Laboratory of Intelligent Computing Signal Processing Ministry of Education Anhui University Hefei230601 China

ISBN: (纸本)9781510639492

A spatial light modulator based on inf-wavelength gold grating structure, named GLCoS by us, has been devised and tested to meet the challenge of the high space-bandwidth product in holographic video display. A sample GLCoS has been made and its display color appears green. However, if it is to be a device of a display system, its color characteristics must be further investigated, that is, its ability to display RGB color and its color purity. There are two MIM (Metal-Insulator-Metal) in the GLCoS, inf-wavelength gold grating plus liquid crystal cell and aluminum electrode forms a hybridized MIM and inf-wavelength gold grating itself is a MIM acting as an open-end TM-FP (TM-Fabry-Pérot) resonator. Based on our previous study involving GLCoS theoretical model, simulation software platform (FDTD plus CST Studio Suite) and an experimentally verified sample of single color, we seek an engineering way with simplicity and compatibility in the sense of the technique to investigate the red-green-blue (RGB) color display with GLCoS. Among the huge parameter space including the geometry and size of the structure, material, wavelength and light incident angle. We choose to change width of the slit, incident angle, LC (liquid crystal) birefringence to find the appropriate GLCoS spectral characteristics. The simulation results show that the dynamic modulation of the RGB phase can be achieved in the visible light band, and its amount of phase modulation is close to 2π and high chromatographic purity. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Light modulators

来源：评论

学校读者我要写书评

暂无评论

Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image

arXiv

引用

arXiv 2024年

作者： Jiao, Pengkun Zhao, Na Chen, Jingjing Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Singapore University of Technology and Design Singapore

Open-vocabulary 3D object detection (OV-3DDet) aims to localize and recognize both seen and previously unseen object categories within any new 3D scene. While language and vision foundation models have achieved success in handling various open-vocabulary tasks with abundant training data, OV-3DDet faces a significant challenge due to the limited availability of training data. Although some pioneering efforts have integrated vision-language models (VLM) knowledge into OV-3DDet learning, the full potential of these foundational models has yet to be fully exploited. In this paper, we unlock the textual and visual wisdom to tackle the open-vocabulary 3D detection task by leveraging the language and vision foundation models. We leverage a vision foundation model to provide image-wise guidance for discovering novel classes in 3D scenes. Specifically, we utilize a object detection vision foundation model to enable the zero-shot discovery of objects in images, which serves as the initial seeds and filtering guidance to identify novel 3D objects. Additionally, to align the 3D space with the powerful vision-language space, we introduce a hierarchical alignment approach, where the 3D feature space is aligned with the vision-language feature space using a pre-trained VLM at the instance, category, and scene levels. Through extensive experimentation, we demonstrate significant improvements in accuracy and generalization, highlighting the potential of foundation models in advancing open-vocabulary 3D object detection in real-world scenarios. © 2024, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Exploring Receptance Weighted key Value Model for Single-Channel Speech Enhancement

Exploring Receptance Weighted Key Value Model for Single-Cha...

引用

IEEE International Conference on Information Communication and signal processing (ICICSP)

作者： Yuanle Li Yi Zhou Hongqing Liu School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China Chongqing Key Laboratory of Signal and Information Processing CQUPT Chongqing China Intelligent Speech and Audio Research Lab (ISARL) CQUPT Chongqing China

ISBN: (数字)9798350355895

ISBN: (纸本)9798350355901

Speech enhancement has significantly benefited from advancements in deep learning, particularly in terms of intelligibility and perceptual quality. Traditional time-frequency (TF) domain methods rely on convolutional neural networks (CNNs) or recurrent neural networks (RNNs) to predict TF masks or speech spectra. In this study, we introduce a novel network architecture, the Receptance Weighted key Value (RWKV) model integrated with the Deep Complex Convolution Recurrent Network (DC-CRN), aimed at effectively training complex targets. This model combines the strengths of RNNs and Transformers, redefining the attention mechanism for speech enhancement tasks to avoid the exponential growth in computational complexity typically associated with traditional Transformer models. Through a series of experiments on the VoiceBank+Demand dataset, the RWKV-DCCRN model has demonstrated superior performance, efficiency, and scalability in handling long-range dependencies compared to traditional DCCRN models. Our implementation showcases the potential to optimize computational efficiency and performance in real-time speech enhancement applications, making it particularly suitable for environments with varying noise conditions and for devices requiring low latency processing.

关键词： Performance evaluation Training Time-frequency analysis Computational modeling Scalability Refining Speech enhancement Transformers Real-time systems Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Broadband High Gain Composite VHF Monopole Antenna Design

Broadband High Gain Composite VHF Monopole Antenna Design

引用

IEEE International Conference on Electronic Information and Communication Technology (ICEICT)

作者： Lihua Wang Baofeng Cao Peng Li Zongxiang Li Yingsong Li College of Information and Communication Engineering Harbin Engineering University Harbin China State Key Laboratory of Nuclear and Biochemical Calamity Protection for Civilian Beijing China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

A novel wideband miniaturized composite monopole antenna is proposed, analysed and investigated in detail, where the antenna consists of a conical monopole structure with a loaded capacitive disc. The antenna is composed of multiple nested section, aiming to reduce the profile of the antenna. The loading disc at its top is equivalent to a capacitive structure to improve the antenna matching and the stability of the pattern. According to the simulation results, the impedance bandwidth $(\mathbf{S}_{\mathbf{11}} < -\mathbf{10})$ is 132.9% $(\mathbf{60.45}\sim \mathbf{300}\ \mathbf{MHz})$ , or even wider. The gain at the entire frequency averages 3 dBi. The performance of the antenna is very suitable for remote wireless communication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning

Masked Video Distillation: Rethinking Masked Feature Modelin...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Rui Wang Dongdong Chen Zuxuan Wu Yinpeng Chen Xiyang Dai Mengchen Liu Lu Yuan Yu–Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Microsoft Cloud + AI

Benefiting from masked visual modeling, self-supervised video representation learning has achieved remarkable progress. However, existing methods focus on learning representations from scratch through reconstructing low-level features like raw pixel values. In this paper, we propose masked video distillation (MVD), a simple yet effective two-stage masked feature modeling framework for video representation learning: firstly we pretrain an image (or video) model by recovering low-level features of masked patches, then we use the resulting features as targets for masked feature modeling. For the choice of teacher models, we observe that students taught by video teachers perform better on temporally-heavy video tasks, while image teachers transfer stronger spatial representations for spatially-heavy video tasks. Visualization analysis also indicates different teachers produce different learned patterns for students. To leverage the advantage of different teachers, we design a spatial-temporal co-teaching method for MVD. Specifically, we distill student models from both video teachers and image teachers by masked feature modeling. Extensive experimental results demonstrate that video transformers pre-trained with spatial-temporal co-teaching outperform models distilled with a single teacher on a multitude of video datasets. Our MVD with vanilla ViT achieves state-of-the-art performance compared with previous methods on several challenging video downstream tasks. For example, with the ViT-Large model, our MVD achieves 86.4% and 76.7% Top-1 accuracy on Kinetics-400 and Something-Something-v2, outperforming VideoMAE by 1.2% and 2.4% respectively. When a larger ViT-Huge model is adopted, MVD achieves the state-of-the-art performance with 77.3% Top-1 accuracy on Something-Something-v2. Code will be available at https://***/ruiwang2021/mvd.

关键词：

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：