检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yu Wang Pengchong Qiao Chang Liu Guoli Song Xiawu Zheng Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science(AI4S)-Preferred Program Peking University Shenzhen Graduate School China Peng Cheng Laboratory Shenzhen China Department of Automation and BNRist Tsinghua University Beijing China

Recent advances in robust semi-supervised learning (SSL) typically filter out-of-distribution (OOD) information at the sample level. We argue that an overlooked problem of robust SSL is its corrupted information on semantic level, practically limiting the development of the field. In this paper, we take an initial step to explore and propose a unified framework termed OOD Semantic Pruning (OSP), which aims at pruning OOD semantics out from in-distribution (ID) features. Specifically, (i) we propose an aliasing OOD matching module to pair each ID sample with an OOD sample with semantic overlap. (ii) We design a soft orthogonality regularization, which first transforms each ID feature by suppressing its semantic component that is collinear with paired OOD sample. It then forces the predictions before and after soft orthogonality decomposition to be consistent. Being practically simple, our method shows a strong performance in OOD detection and ID classification on challenging benchmarks. In particular, OSP surpasses the previous state-of-the-art by 13.7% on accuracy for ID classification and 5.9% on AUROC for OOD detection on TinyImageNet dataset. The source codes are publicly available at https://***/rain305f/OSP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DiffusionRet: Generative Text-Video Retrieval with Diffusion Model

DiffusionRet: Generative Text-Video Retrieval with Diffusion...

引用

International Conference on computer Vision (ICCV)

作者： Peng Jin Hao Li Zesen Cheng Kehan Li Xiangyang Ji Chang Liu Li Yuan Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Shenzhen China Department of Automation and BNRist Tsinghua University Beijing China Peng Cheng Laboratory Shenzhen China

Existing text-video retrieval solutions are, in essence, discriminant models focused on maximizing the conditional likelihood, i.e., p(candidates|query). While straightforward, this de facto paradigm overlooks the underlying data distribution p(query), which makes it challenging to identify out-of-distribution data. To address this limitation, we creatively tackle this task from a generative viewpoint and model the correlation between the text and the video as their joint probability p(candidates,query). This is accomplished through a diffusion-based text-video retrieval framework (Diffusion-Ret), which models the retrieval task as a process of gradually generating joint distribution from noise. During training, DiffusionRet is optimized from both the generation and discrimination perspectives, with the generator being optimized by generation loss and the feature extractor trained with contrastive loss. In this way, DiffusionRet cleverly leverages the strengths of both generative and discriminative methods. Extensive experiments on five commonly used text-video retrieval benchmarks, including MSRVTT, LSMDC, MSVD, ActivityNet Captions, and DiDeMo, with superior performances, justify the efficacy of our method. More encouragingly, without any modification, DiffusionRet even performs well in out-domain retrieval settings. We believe this work brings fundamental insights into the related fields. Code is available at https://***/jpthu17/DiffusionRet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer Normalization

LaPE: Layer-adaptive Position Embedding for Vision Transform...

引用

International Conference on computer Vision (ICCV)

作者： Runyi Yu Zhennan Wang Yinhuai Wang Kehan Li Chang Liu Haoyi Duan Xiangyang Ji Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School China Peng Cheng Laboratory Shenzhen China Department of Automation and BNRist Tsinghua University Beijing China School of Computer Science and Technology Zhejiang University Zhejiang China

Position information is critical for Vision Transformers (VTs) due to the permutation-invariance of self-attention operations. A typical way to introduce position information is adding the absolute Position Embedding (PE) to patch embedding before entering VTs. However, this approach operates the same Layer Normalization (LN) to token embedding and PE, and delivers the same PE to each layer. This results in restricted and monotonic PE across layers, as the shared LN affine parameters are not dedicated to PE, and the PE cannot be adjusted on a per-layer basis. To overcome these limitations, we propose using two independent LNs for token embeddings and PE in each layer, and progressively delivering PE across layers. By implementing this approach, VTs will receive layer-adaptive and hierarchical PE. We name our method as Layer-adaptive Position Embedding, abbreviated as LaPE, which is simple, effective, and robust. Extensive experiments on image classification, object detection, and semantic segmentation demonstrate that LaPE significantly outperforms the default PE method. For example, LaPE improves +1.06% for CCT on CIFAR100, +1.57% for DeiT-Ti on ImageNet-1K, +0.7 box AP and +0.5 mask AP for ViT-Adapter-Ti on COCO, and +1.37 mIoU for tiny Segmenter on ADE20K. This is remarkable considering LaPE only increases negligible parameters, memory, and computational cost.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Floor plan construction via anonymous Wi-Fi signal fragment matching

引用

ICIC Express Letters, Part B: Applications 2014年第4期5卷 981-987页

作者： Zhou, Mu Tian, Zengshan Xu, Kunjie Tang, Xiaomou Wang, Zhuoran Chongqing Key Lab of Mobile Communications Technology School of Communication and Information Engineering Chongqing University of Posts and Telecommunications No. 2 Chongwen Road Nan'an Dist. Chongqing 400065 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong Graduate Telecommunications and Networking Program University of Pittsburgh PA 15260 United States

Floor plan construction is the basis for fingerprint-based localization and people's activity learning, especially in the environments where the geometrical map is not available or does not exist. To this end, we propose a new received signal strength (RSS) fragment matching approach to identify the location points (LPs) in floor plan as the overlapped pieces between the fragments. Then, by means of the Smith-Waterman alignment, each LP can be recognized as a winning path in scoring space. Finally, we use the Allen's interval algebra to assemble the time-stamped LPs into a floor plan in target area. The experiments with the actual Wi-Fi RSS measurements recorded in HKUST campus demonstrate that our proposed approach performs better than the conventional K-means clustering and spectral clustering in floor plan construction. © 2014 ICIC International.

关键词： Algebra

来源：评论

学校读者我要写书评

暂无评论

Construction of time-stamped mobility map for path tracking via smith-waterman measurement matching

引用

Mathematical Problems in engineering 2014年第1期2014卷

作者： Zhou, Mu Tian, Zengshan Xu, Kunjie Wu, Haibo Pu, Qiaolin Yu, Xiang Chongqing Key Lab of Mobile Communications Technology Chongqing University of Posts and Telecommunications Chongqing 400065 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong Graduate Telecommunications and Networking Program University of Pittsburgh Pittsburgh PA 15260 United States China Internet Research Lab Computer Network Information Center Chinese Academy of Sciences Beijing 100190 China

Path tracking in wireless and mobile environments is a fundamental technology for ubiquitous location-based services (LBSs). In particular, it is very challenging to develop highly accurate and cost-efficient tracking systems applied to the anonymous areas where the floor plans are not available for security and privacy reasons. This paper proposes a novel path tracking approach for large Wi-Fi areas based on the time-stamped unlabeled mobility map which is constructed from Smith-Waterman received signal strength (RSS) measurement matching. Instead of conventional location fingerprinting, we construct mobility map with the technique of dimension reduction from the raw measurement space into a low-dimensional embedded manifold. The feasibility of our proposed approach is verified by the real-world experiments in the HKUST campus Wi-Fi networks, sMobileNet. The experimental results prove that our approach is adaptive and capable of achieving an adequate precision level in path tracking. © 2014 Mu Zhou et al.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation for Segmentation with Black-box Source Model

arXiv

引用

arXiv 2022年

作者： Liu, Xiaofeng Yoo, Chaehwa Xing, Fangxu Kuo, C.-C. Jay Fakhri, Georges El Kang, Je-Won Woo, Jonghye Gordon Center for Medical Imaging Massachusetts General Hospital Harvard Medical School BostonMA United States Dept. of Electronic and Electrical Engineering and Graduate Program in Smart Factory Ewha Womans University Seoul Korea Republic of Dept. of Electrical and Computer Engineering University of Southern California Los AngelesCA United States

Unsupervised domain adaptation (UDA) has been widely used to transfer knowledge from a labeled source domain to an unlabeled target domain to counter the difficulty of labeling in a new domain. The training of conventional solutions usually relies on the existence of both source and target domain data. However, privacy of the large-scale and well-labeled data in the source domain and trained model parameters can become the major concern of cross center/domain collaborations. In this work, to address this, we propose a practical solution to UDA for segmentation with a black-box segmentation model trained in the source domain only, rather than original source data or a white-box source model. Specifically, we resort to a knowledge distillation scheme with exponential mixup decay (EMD) to gradually learn target-specific representations. In addition, unsupervised entropy minimization is further applied to regularization of the target domain confidence. We evaluated our framework on the BraTS 2018 database, achieving performance on par with white-box source model adaptation approaches. © 2022, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning

Video-Text as Game Players: Hierarchical Banzhaf Interaction...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Peng Jin Jinfa Huang Pengfei Xiong Shangxuan Tian Chang Liu Xiangyang Ji Li Yuan Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Shenzhen China Shopee Shenzhen China Department of Automation and BNRist Tsinghua University Beijing China Peng Cheng Laboratory Shenzhen China

Contrastive learning-based video-language representation learning approaches, e.g., CLIP, have achieved outstanding performance, which pursue semantic interaction upon pre-defined video-text pairs. To clarify this coarse-grained global interaction and move a step further, we have to encounter challenging shell-breaking interactions for fine-grained cross-modal learning. In this paper, we creatively model video-text as game players with multivariate cooperative game theory to wisely handle the uncertainty during fine-grained semantic interaction with diverse granularity, flexible combination, and vague intensity. Concretely, we propose Hierarchical Banzhaf Interaction (HBI) to value possible correspondence between video frames and text words for sensitive and explainable cross-modal contrast. To efficiently realize the cooperative game of multiple video frames and multiple text words, the proposed method clusters the original video frames (text words) and computes the Banzhaf Interaction between the merged tokens. By stacking token merge modules, we achieve cooperative games at different semantic levels. Extensive experiments on commonly used text-video retrieval and video-question answering bench-marks with superior performances justify the efficacy of our HBI. More encouragingly, it can also serve as a visualization tool to promote the understanding of cross-modal interaction, which have a far-reaching impact on the community. Project page is available at https://***/HBI/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Capturing Cellular Communication with Guided Electrode Network on a Silicon Integrated Circuit Chip

Capturing Cellular Communication with Guided Electrode Netwo...

引用

2006 8th International Conference on Solid-State and Integrated Circuit Technology

作者： Mansun Chan Chi-Kong Yeung Yijin Wang Jin He Sven Ingebrandt Andreas Offenhaeusser Dept.of Electronic and Computer Engineering Hong Kong University of Science & Technology Bioengineering Graduate Program Hong Kong University of Science & Technology Institute of Microelectronic Peking University Juelich Research Center Institute for Thin Films and Interfaces(ISG-2)Leo-Brandt Str.52425 JuelichGermany

ISBN: (纸本)1424401607

This paper describes the development of a Multi-Electrode Array(MEA)with Guided Network for Cell-to-Cell Communication Transduction using a standard integrated circuit(IC) fabrication *** conventional electronic system,bio-system requires a special handling environment that is uncommon in conventional IC *** work presented here demonstrated the interaction between electrically active cells such as neuron and cardiac cells and an IC based *** a carefully designed array,and ionic action of a cell, extracellular signals can be captured and imaged.

关键词： Capturing Cellular Communication with Guided Electrode Network on a Silicon Integrated Circuit Chip

来源：评论

学校读者我要写书评

暂无评论

ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation

ACSeg: Adaptive Conceptualization for Unsupervised Semantic ...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Kehan Li Zhennan Wang Zesen Cheng Runyi Yu Yian Zhao Guoli Song Chang Liu Li Yuan Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Shenzhen China Peng Cheng Laboratory Shenzhen China Dalian University of Technology Department of Automation and BNRist Tsinghua University Beijing China

Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level semantic relationships, significantly promoting the development of unsupervised dense prediction tasks, e.g., unsupervised semantic segmentation (USS). The extracted relationship among pixel-level representations typically contains rich class-aware information that semantically identical pixel embeddings in the representation space gather together to form sophisticated concepts. However, leveraging the learned models to ascertain semantically consistent pixel groups or regions in the image is non-trivial since over/ under-clustering overwhelms the conceptualization procedure under various semantic distributions of different images. In this work, we investigate the pixel-level semantic aggregation in self-supervised ViT pre-trained models as image Segmentation and propose the Adaptive Conceptualization approach for USS, termed ACSeg. Concretely, we explicitly encode concepts into learnable prototypes and design the Adaptive Concept Generator (ACG), which adaptively maps these prototypes to informative concepts for each image. Meanwhile, considering the scene complexity of different images, we propose the modularity loss to optimize ACG independent of the concept number based on estimating the intensity of pixel pairs belonging to the same concept. Finally, we turn the USS task into classifying the discovered concepts in an unsupervised manner. Extensive experiments with state-of-the-art results demonstrate the effectiveness of the proposed ACSeg.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Utilizing Educational Robotics for Learning About Sustainability Issues

Utilizing Educational Robotics for Learning About Sustainabi...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Andre Carlos Teixeira de Vasconcelos Almir Silva Silveira Raphael Melo de Oliveira Lucas Tejedor da Silva Giselle Medeiros Mesiara João Roberto de Toledo Quadros Master's Degree Program in Computer Science Celso Suckow da Fonseca Federal Technological Education Center Rio de Janeiro Brazil Department of Computer Science Celso Suckow da Fonseca Federal Technological Education Center Rio de Janeiro Brazil Sense & Learn (SELEA)21 Copenhagen University Denmark Department of Electronic Engineering/Pos-Graduate Program in Computer Science Celso Suckow da Fonseca Federal Technological Education Center Rio de Janeiro Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

Nowadays, schools are trying to insert knowledge and learning about sustainability issues and environmental conservation in the academic context from an early age. It is also observed the use of information technology with new didactic and ludic resources that can encourage elementary and high school students to obtain knowledge about sustainability. To this end, this research presents some results using Educational Robotics, Gestalt, and information technology, which students received from a Brazilian public elementary school. In this study, after attending workshops on sustainability, the students developed robotic resources to help them with sustainability-related knowledge. The resources were tested according to their objectives: a mobile robot that recognizes the food and shows its footprint and a box with gas sensors to identify if food is in consumable condition or should be recycled. The experiment was very successful and is in a continuous application phase.

关键词： Conferences Education Robot sensing systems Object recognition Mobile robots Sustainable development Information technology

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：