检索结果-内蒙古大学图书馆

27th European Conference on Artificial intelligence, ECAI 2024

作者： Diao, Yujie Yu, Ruiguo Li, Xuewei Fan, Yilong Liu, Zhiqiang Yu, Mei Wang, Chenhan Gao, Jie College of Intelligence and Computing Tianjin University Tianjin300350 China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin300350 China Tianjin Key Laboratory of Advanced Networking Tianjin300350 China School of Future Technology Tianjin University Tianjin300350 China IT Co. Ltd. Tianjin300456 China

ISBN: (纸本)9781643685489

Refining the seed region to obtain finely annotated pseudo masks for training a segmentation model is a crucial step in the multi-stage weakly supervised semantic segmentation (WSSS) framework. One of the most popular refinement methods, IRN, extends seed regions towards the edges in the image. However, we observed that, due to the lack of guidance from semantic information, IRN's refinement may lead the generation of partially erroneous refinement directions. To address this issue, we leverage prototypes to recover the overlooked category semantic information in the refinement stage. We propose a prototype-based pseudo mask reclassification post-processing (PtReCl) to correct misclassified pixels in the pseudo masks, generating refined pseudo masks with more accurate coverage. Experimental evaluations demonstrate that our post-processing approach brings improvements in both pseudo mask quality and segmentation results on PASCAL VOC and MS COCO datasets, achieving state-of-the-art performance on VOC. © 2024 The Authors.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Exploiting Polarized Material Cues for Robust Car Detection

arXiv

引用

arXiv 2024年

作者： Dong, Wen Mei, Haiyang Wei, Ziqi Jin, Ao Qiu, Sen Zhang, Qiang Yang, Xin Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology China Show Lab National University of Singapore Singapore Institute of Automation Chinese Academy of Sciences China State Key Laboratory of Structural Analysis for Industrial Equipment Dalian University of Technology China

Car detection is an important task that serves as a crucial prerequisite for many automated driving functions. The large variations in lighting/weather conditions and vehicle densities of the scenes pose significant challenges to existing car detection algorithms to meet the highly accurate perception demand for safety, due to the unstable/limited color information, which impedes the extraction of meaningful/discriminative features of cars. In this work, we present a novel learning-based car detection method that leverages trichromatic linear polarization as an additional cue to disambiguate such challenging cases. A key observation is that polarization, characteristic of the light wave, can robustly describe intrinsic physical properties of the scene objects in various imaging conditions and is strongly linked to the nature of materials for cars (e.g., metal and glass) and their surrounding environment (e.g., soil and trees), thereby providing reliable and discriminative features for robust car detection in challenging scenes. To exploit polarization cues, we first construct a pixel-aligned RGB-Polarization car detection dataset, which we subsequently employ to train a novel multimodal fusion network. Our car detection network dynamically integrates RGB and polarization features in a request-and-complement manner and can explore the intrinsic material properties of cars across all learning samples. We extensively validate our method and demonstrate that it outperforms state-of-the-art detection methods. Experimental results show that polarization is a powerful cue for car detection. Our code is available at https://***/wind1117/AAAI24-PCDNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

DFGET: Displacement-Field Assisted Graph Energy Transmitter for Gland Instance Segmentation 17

DFGET: Displacement-Field Assisted Graph Energy Transmitter ...

引用

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Jian, Caiqing Qin, Yongbin Wang, Lihui Ye, Chen Cheng, Xinyu Guizhou University Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang China

ISBN: (纸本)9798350387384

Gland instance segmentation is an essential but challenging task in the diagnosis of adenocarcinoma. The existing models usually achieve gland instance segmentation through multi-task learning and boundary loss constraint. However, how to deal with the problems of gland adhesion and inaccurate boundary in segmenting the complex samples remains a challenge. In this work, we propose a novel geometric feature named displacement field (DF), which can represent the geometric information such as shape, size, and orientation of the glands. Based on the explicit constraint of DF, a displacement-field assisted graph energy transmitter (DFGET) framework is proposed for solving the above problems. Using such graph framework, the gland semantic segmentation map and the displacement field of the graph nodes are estimated with two graph network branches. With the constraint of DF, a graph cluster module is presented to improve the intra-class feature consistency and inter-class feature discrepancy, as well as to separate the adherent glands. Extensive comparison and ablation experiments on the GlaS dataset demonstrate the effectiveness of the displacement field and the superiority of DFGET. Compared to the best comparative model, DFGET increases the object-Dice and object-F1 score by 2.27% and 3.11% respectively, while decreases the object-HD by 15.58, achieving state-of-the-art performance, which indicates that DFGET can serve as an auxiliary tool for the diagnosis of adenocarcinoma. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

PM2: A New Prompting Multi-modal Model Paradigm for Few-shot Medical Image Classification

PM2: A New Prompting Multi-modal Model Paradigm for Few-shot...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhenwei Wang Qiule Sun Bingbing Zhang Weijian Su Pengfei Wang Jianxin Zhang Qiang Zhang Key Laboratory of Social Computing and Cognitive Intelligence (Ministry of Education) Dalian University of Technology China School of Computer Science and Technology Dalian University of Technology China School of Computer Science and Engineering Dalian Minzu University China School of Information and Communication Engineering Dalian University of Technology China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Few-shot learning has become a key technical solution for addressing the challenges of limited data and difficult annotation acquisition in medical image classification. However, relying solely on a single image modality proves inadequate for capture conceptual categories. This paper proposes a novel medical image classification paradigm based on a multi-modal foundation model, called PM 2 . In addition to the image modality, PM 2 introduces supplementary text input (prompt) to further describe images or conceptual categories and facilitate cross-modal few-shot learning. We empirically studied five different prompting schemes under this new paradigm. Furthermore, linear probing in multi-modal models only takes class token as input, ignoring the rich statistical data contained in high-level visual tokens. Therefore, we alternately perform linear classification on the feature distributions of visual tokens and class token. To effectively extract statistical information, we use global covariance pool with efficient matrix power normalization to aggregate the visual tokens. We then combine two classification heads: one for handling image class token and prompt representations encoded by the text encoder, and the other for classifying the feature distributions of visual tokens. Experiments on two medical datasets demonstrate that regardless of the prompting scheme, our method PM 2 outperforms its counterparts, achieving state-of-the-art performance.

关键词： Visualization Head Foundation models Feature extraction Data models Data mining Few shot learning Covariance matrices Medical diagnostic imaging Image classification

来源：评论

学校读者我要写书评

暂无评论

Apprenticeship-Inspired Elegance: Synergistic Knowledge Distillation Empowers Spiking Neural Networks for Efficient Single-Eye Emotion Recognition

arXiv

引用

arXiv 2024年

作者： Wang, Yang Mei, Haiyang Bao, Qirui Wei, Ziqi Shou, Mike Zheng Li, Haizhou Dong, Bo Yang, Xin Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology China National Univerisity of Singapore Singapore Institute of Automation Chinese Academy of Sciences China Independent Researcher China

We introduce a novel multimodality synergistic knowledge distillation scheme tailored for efficient single-eye motion recognition tasks. This method allows a lightweight, unimodal student spiking neural network (SNN) to extract rich knowledge from an event-frame multimodal teacher network. The core strength of this approach is its ability to utilize the ample, coarser temporal cues found in conventional frames for effective emotion recognition. Consequently, our method adeptly interprets both temporal and spatial information from the conventional frame domain, eliminating the need for specialized sensing devices, e.g., event-based camera. The effectiveness of our approach is thoroughly demonstrated using both existing and our compiled single-eye emotion recognition datasets, achieving unparalleled performance in accuracy and efficiency over existing state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Audio-Visual Co-Learning for Text-Independent Speaker Verification 48

Cross-Modal Audio-Visual Co-Learning for Text-Independent Sp...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Liu, Meng Lee, Kong Aik Wang, Longbiao Zhang, Hanyi Zeng, Chang Dang, Jianwu Tianjin University College of Intelligence and Computing Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Astar Institute for Infocomm Research Singapore Singapore Institute of Technology Singapore National Institute of Informatics Tokyo Japan

ISBN: (纸本)9781728163277

Visual speech (i.e., lip motion) is highly related to auditory speech due to the co-occurrence and synchronization in speech production. This paper investigates this correlation and proposes a cross-modal speech co-learning paradigm. The primary motivation of our cross-modal co-learning method is modeling one modality aided by exploiting knowledge from another modality. Specifically, two cross-modal boosters are introduced based on an audio-visual pseudo-siamese structure to learn the modality-transformed correlation. Inside each booster, a max-feature-map embedded Transformer variant is proposed for modality alignment and enhanced feature generation. The network is co-learned both from scratch and with pretrained models. Experimental results on the test scenarios demonstrate that our proposed method achieves around 60% and 20% average relative performance improvement over baseline unimodal and fusion systems, respectively. © 2023 IEEE.

关键词： co-learning cross-modal lip biometrics speaker verification visual speech

来源：评论

学校读者我要写书评

暂无评论

Research on the classification method of knowledge question intention for Tibetan language curriculum 5

Research on the classification method of knowledge question ...

引用

5th ACM International Conference on Multimedia in Asia, MMAsia 2023 Workshops

作者： Qie, Yangzhuoma Khysru, Kuntharrgyal Wan, Maji Wei, Jianguo Key Laboratory of Artificial Intelligence Application Technology Qinghai Minzu University Xining China Henan county middle school for Nationalities Henan Qinghai China Key Laboratory of Artificial Intelligence Application Technology State Ethnic Affairs Commission Qinghai Minzu University Xining China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin University Tianjin China

ISBN: (纸本)9798400703263

As an important part of the intelligent question-answering system, intention classification has attracted more and more researchers’ attention. Tibetan corpus is different from other common corpora. Its grammatical structure is relatively complex, and there is no large amount of labeled data, which makes the research of intention classification in this field scarce. Given the above problems, this paper takes Tibetan curriculum knowledge as an example and introduces the ZangBert-BiLSTM modeling question intention classification task. Firstly, ZangBert encodes the semantic information in the text sequence. In modeling the semantic information, the function word information is introduced by inserting special flag bits into the sequence. Then, the BiLSTM model is used to model the long-distance dependence information in the semantic information sequence. Finally, these text features are sent to the downstream classifier for intention classification. In order to verify the validity of the question intention classification model of primary school Tibetan curriculum knowledge, the corresponding question intention classification data set is labeled, and good intention classification performance is obtained on the data set, which verifies the validity of the work done in this paper. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Augmenting Short Enrollment Speech via Synthesis for Target Speaker Extraction

Augmenting Short Enrollment Speech via Synthesis for Target ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Huang, Zikang Lin, Jingru Ge, Meng Jiang, Yu Wang, Xiaobao Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Shenzhen China Department of Electrical and Computer and Engineering National University of Singapore Singapore Co. Ltd. Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9798350368741

A high-quality enrollment speech is crucial to target speaker extraction (TSE), since it provides essential cues for identifying the target speaker in the mixture. However, real applications usually only permit a short enrollment speech, e.g. a wakeup word for a mobile device, that provides limited cues. To address this issue, we propose an enrollment augmentation strategy that allows us to enrich the limited enrollment speech with massive text data through speech synthesis. By doing so, the extended enrollment speech contains enhanced speaker timbre and phonetic content which leads to better extraction quality. Furthermore, we propose a training data augmentation strategy to improve the model's robustness and generalization in short enrollment speech scenarios. Experiments on Libri2Mix demonstrate that our proposed strategies bring a significant improvement in extreme scenarios where only 0.5s and 1-word enrollment speech is provided. We also release our code at https://***/HuangZikang-TJU/Aug4TSE. © 2025 IEEE.

关键词： continue speaking data augmentation short enrollment speech synthesis Target speaker extraction

来源：评论

学校读者我要写书评

暂无评论

PM2: A New Prompting Multi-modal Model Paradigm for Few-shot Medical Image Classification

arXiv

引用

arXiv 2024年

作者： Wang, Zhenwei Sun, Qiule Zhang, Bingbing Wang, Pengfei Zhang, Jianxin Zhang, Qiang Key Laboratory of Social Computing and Cognitive Intelligence Ministry of Education Dalian University of Technology Dalian116024 China School of Computer Science and Technology Dalian University of Technology Dalian116024 China School of Computer Science and Engineering Dalian Minzu University Dalian116600 China School of Information and Communication Engineering Dalian University of Technology Dalian116024 China

Few-shot learning has been successfully applied to medical image classification as only very few medical examples are available for training. Due to the challenging problem of limited number of annotated medical images, image representations should not be solely derived from a single image modality which is insufficient for characterizing concept classes. In this paper, we propose a new prompting multi-modal model paradigm on medical image classification based on multi-modal foundation models, called PM2. Besides image modality, PM2 introduces another supplementary text input, known as prompt, to further describe corresponding image or concept classes and facilitate few-shot learning across diverse modalities. To better explore the potential of prompt engineering, we empirically investigate five distinct prompt schemes under the new paradigm. Furthermore, linear probing in multi-modal models acts as a linear classification head taking as input only class token, which ignores completely merits of rich statistics inherent in high-level visual tokens. Thus, we alternatively perform a linear classification on feature distribution of visual tokens and class token simultaneously. To effectively mine such rich statistics, a global covariance pooling with efficient matrix power normalization is used to aggregate visual tokens. Then we study and combine two classification heads. One is shared for class token of image from vision encoder and prompt representation encoded by text encoder. The other is to classification on feature distribution of visual tokens from vision encoder. Extensive experiments on three medical datasets show that our PM2 significantly outperforms counterparts regardless of prompt schemes and achieves state-of-the-art performance. © 2024, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Anomalous Behavior Identification with Visual Federated Learning in Multi-UAVs Systems

Anomalous Behavior Identification with Visual Federated Lear...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Pengfei Wang Xinrui Yu Yefei Ye Heng Qi Shuo Yu Leyou Yang Qiang Zhang School of Computer Science and Technology Dalian University of Technology Dalian China Ministry of Education Key Laboratory of Social Computing and Cognitive Intelligence (Dalian University of Technology) Dalian China School of Computer Science and Engineering Northeastern University Shenyang China

Anomaly detection aims to identify data or behav-iors that are different from the usual patterns. In traditional anomaly detection settings, edge devices collect the data and send it to a centralized server for model training, which faces two critical issues: (1) it risks data exposure during transmission; (2) it demands a large amount of network bandwidth for data transfer. To tackle these problems, we propose a Visual Federated Learning algorithm (VFLA) for anomalous behavior identification in the multi-UAVs system. To the best of our knowledge, we are the first to merge federated learning with video-based anomaly detection. VFLA consists of two phases: The initial phase is training a pseudo-label generator. UAVs collect a dataset and manually annotate it. This labeled data is then used to train the pseudo-label generator on the server, which is subsequently distributed back to the UAVs. The second phase is the federated learning-based anomaly detection model training. UAVs leverage the pseudo-label generator to automatically annotate the collected video footage. These annotated videos are fed into an anomaly detection network for training. Once the local training is completed, UAVs upload their local models to a server for federated aggregation. The global model is then redistributed to the UAVs for additional training rounds, until reach the target accuracy. Finally, we simulate the federated learning anomaly detection algorithm on the Shanghai-tech dataset, it demonstrates an average accuracy boost of 5.6% compared to baselines.

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：