检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Jiang, Jing Deng, Weihong The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China

In this paper, we aim to improve the performance of in-the-wild Facial Expression recognition (FER) by exploiting semi-supervised learning. Large-scale labeled data and deep learning methods have greatly improved the performance of image recognition. However, the performance of FER is still not ideal due to the lack of training data and incorrect annotations (e.g., label noises). Among existing in-the-wild FER datasets, reliable ones contain insufficient data to train robust deep models while large-scale ones are annotated in lower quality. To address this problem, we propose a semi-supervised learning algorithm named Progressive Teacher (PT) to utilize reliable FER datasets as well as large-scale unlabeled expression images for effective training. On the one hand, PT introduces semi-supervised learning method to relieve the shortage of data in FER. On the other hand, it selects useful labeled training samples automatically and progressively to alleviate label noise. PT uses selected clean labeled data for computing the supervised classification loss and unlabeled data for unsupervised consistency loss. Experiments on widely-used databases RAF-DB and FERPlus validate the effectiveness of our method, which achieves state-of-the-art performance with accuracy of 89.57% on RAF-DB. Additionally, when the synthetic noise rate reaches even 30%, the performance of our PT algorithm only degrades by 4.37%. Copyright © 2022, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Face recognition with Clustering based Domain Adaptation

arXiv

引用

arXiv 2022年

作者： Wang, Mei Deng, Weihong The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China

Despite great progress in face recognition tasks achieved by deep convolution neural networks (CNNs), these models often face challenges in real world tasks where training images gathered from Internet are different from test images because of different lighting condition, pose and image quality. These factors increase domain discrepancy between training (source domain) and testing (target domain) database and make the learnt models degenerate in application. Meanwhile, due to lack of labeled target data, directly fine-tuning the prelearnt models becomes intractable and impractical. In this paper, we propose a new clustering-based domain adaptation method designed for face recognition task in which the source and target domain do not share any classes. Our method effectively learns the discriminative target feature by aligning the feature domain globally, and, at the meantime, distinguishing the target clusters locally. Specifically, it first learns a more reliable representation for clustering by minimizing global domain discrepancy to reduce domain gaps, and then applies simplified spectral clustering method to generate pseudo-labels in the domain-invariant feature space, and finally learns discriminative target representation. Comprehensive experiments on widely-used GBU, IJB-A/B/C and RFW databases clearly demonstrate the effectiveness of our newly proposed approach. State-of-the-art performance of GBU data set is achieved by only unsupervised adaptation from the target training data. © 2022, CC BY.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Vehicle Routing Problem with Time Windows using Hybrid Metaheuristic Dragonfly Algorithm and Variable Neighborhood Search: Work on Progress 11

Vehicle Routing Problem with Time Windows using Hybrid Metah...

引用

11th International Conference on Electrical Engineering, Computer Science and Informatics, EECSI 2024

作者： Yunita, Yunita Stiawan, Deris Rini, Dian Palupi Sriwijaya University Faculty of Computer Science Indonesia Sriwijaya University Intelligent System Research Group Faculty of Computer Science South Sumatera Palembang Indonesia Sriwijaya University Communication Network and Information Security Research Group Faculty of Computer Science South Sumatera Palembang Indonesia Sriwijaya University Image Processing Dan Pattern Recognition Laboratory Group Faculty of Computer Science South Sumatera Palembang Indonesia

ISBN: (纸本)9798350355314

One of the problems with Smart Transportation is the problem of cost and travel time. This problem is known as the Variable Routing Problem (VRP). In some real cases, in addition to considering route selection, there are limitations on the capacity and time period for the vehicle to serve each customer known as Time Windows, so VRP has developed into Variable Routing Problem with Time Windows (VRPTW). One way to solve VRPTW is to use metaheuristic methods. However, the metaheuristic method has a weakness, which are it can get stuck in local optimums and fail to find better global solutions. To overcome this, a combination with other methods or known as hybrid is needed. The formulation of this research problem is how to develop a Smart transportation model using a metaheuristic hybrid algorithm. The purpose of this study is to develop a Smart transportation model using a metaheuristic hybrid algorithm. The method used is to combine two metaheuristic algorithms, which are the Dragonfly Algorithm (DA) and the Variable Neighborhood Search (VNS). The result of this research is a new algorithm model which is a hybrid between DA and VNS. Through a combination of global exploration using DA and local exploitation using VNS, this algorithm is expected to be able to find a better solution and faster convergence in solving VRPTW problems © 2024 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning of Gaussian Mixture Model with Application to Image Segmentation

引用

Chinese Journal of Electronics 2023年第3期19卷 451-456页

作者： Bo Li Wenju Liu Lihua Dou School of Automation Beijing Institute of Technology Beijing China Key Laboratory of Complex System Intelligent Control and Decision Ministry of Education Beijing Institute of Technology Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China

Density estimation via Gaussian mixture modeling has been successfully applied to image segmentation, speech processing and other fields relevant to clustering analysis and Probability density function (PDF) modeling. Finite Gaussian mixture model is usually used in practice and the selection of number of mixture components is a significant problem in its application. For example, in image segmentation, it is the donation of the number of segmentation regions. The determination of the optimal model order therefore is a problem that achieves widely attention. This paper proposes a degenerating model algorithm that could simultaneously select the optimal number of mixture components and estimate the parameters for Gaussian mixture model. Unlike traditional model order selection method, it does not need to select the optimal number of components from a set of candidate models. Based on the investigation on the property of the elliptically contoured distributions of generalized multivariate analysis, it select the correct model order in a different way that needs less operation times and less sensitive to the initial value of EM. The experimental results show the effectiveness of the algorithm.

关键词： Training Image segmentation Analytical models Parameter estimation Estimation Probability density function Speech processing

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Resolution Feature Fusion for Fine-Grained Visual Classification

引用

IEEE Transactions on Circuits and systems for Video Technology 2025年

作者： Yang, Yuqi Chang, Dongliang Du, Ruoyi Song, Yi-Zhe Ma, Zhanyu Beijing University of Posts and Telecommunications Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing100876 China Tsinghua University Department of Automation Beijing100084 China University of Surrey SketchX CVSSP GuildfordGU2 7XH United Kingdom

Despite significant progress, the shortage of labeled data and expert knowledge remains a challenge for Fine-grained Visual Classification (FGVC). Some multi-source approaches that incorporate additional modalities, such as sound or bounding boxes, show promise for data enrichment but introduce added complexity to data collection. In this paper, we pose the question: can multi-source capabilities be achieved solely with existing images? The answer, confirmed by a pilot study, is affirmative. By analyzing the probability distribution of model output with different resolutions image, we find that complementary information beneficial to FGVC exists among images of different resolutions. Although the classification accuracy of low-resolution images is lower than high-resolution images, it can provide additional information for high-resolution input images. We designed a naive baseline that uses mixed training of multi-resolution images. Through the experimental results of the baseline, we find that i) not all low-resolution images are beneficial, and ii) adaptively selecting low-resolution images is what we need. Therefore, we proposed a meta-learning-based adaptive "resolution" pooling layer. Through the pooling operation, the features of low-resolution images are obtained from high-resolution images, and the most appropriate complementary features are selected for the features of high-resolution images through the gating mechanism, which enables the model to fully and autonomously exploit the complementary information. Experimental results on three FGVC datasets validate the effectiveness of our proposed method. Our code is available at https://***/PRIS-CV/Adaptive-Multi-Resolution-Feature-Fusion. © 2025 IEEE. All rights reserved.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization

arXiv

引用

arXiv 2022年

作者： Zhao, Lulu Zheng, Fujia Zeng, Weihao He, Keqing Xu, Weiran Jiang, Huixing Wu, Wei Wu, Yanan Pattern Recognition & Intelligent System Laboratory China Beijing University of Posts and Telecommunications Beijing China Meituan Group Beijing China

The most advanced abstractive dialogue summarizers lack generalization ability on new domains and the existing researches for domain adaptation in summarization generally rely on large-scale pre-trainings. To explore the lightweight fine-tuning methods for domain adaptation of dialogue summarization, in this paper, we propose an efficient and generalizable Domain-Oriented Prefix-tuning model, which utilizes a domain word initialized prefix module to alleviate domain entanglement and adopts discrete prompts to guide the model to focus on key contents of dialogues and enhance model generalization. We conduct zero-shot experiments and build domain adaptation benchmarks on two multi-domain dialogue summarization datasets, TODSum and QMSum. Adequate experiments and qualitative analysis prove the effectiveness of our methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Cd-Vae: An Unsupervised Disentangled Representation Learning Framework for Visual Data

SSRN

引用

SSRN 2023年

作者： Huang, Chengquan Cai, Jianghai Luo, Senyan Wang, Shunxia Yang, Guiyan Lei, Huan Zhou, Lihua Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang550025 China School of Data Science and Information Engineering Guizhou Minzu University Guiyang550025 China

Disentangled representation learning is a crucial research problem in the field of artificial intelligence, and learning meaningful representation of visual data is useful for improving the generalizability and interpretability of machine learning models. To discover and learn the interpretable factors behind the visual data, previous approaches typically use extra regularization terms in learning disentangled representations of the generated images, which usually lead to poor results between disentanglement and generative quality. For the generative model variational auto-encoder (VAE), the traversal of the generated images along different factor directions shows meaningful and interpretable variations in the latent space. Building upon this observation, we argue that it is important to learn disentangled representations of the generated images by exploiting the scalability and training stability of the generative model VAE, and focusing on meaningful traversal directions in the latent space. Therefore, we propose contrast disentanglement based on VAE (CD-VAE), a deep unsupervised disentangled representation learning framework for visual data, that can discover the latent factors in image data. CD-VAE jointly learns disentangled representations by traversing image variations in the latent space, and constructing contrast disentanglement in the variation space. Experimental results demonstrate that CD-VAE can discover interpretable directions and achieve better disentangled representation learning for visual data. Source codes and pre-training data will be publicly available at GitHub website. © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Dual-attention Guided Dropblock Module for Weakly Supervised Object Localization

Dual-attention Guided Dropblock Module for Weakly Supervised...

引用

International Conference on pattern recognition

作者： Junhui Yin Siqing Zhang Dongliang Chang Zhanyu Ma Jun Guo Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications

Attention mechanisms is frequently used to learn the discriminative features for better feature representations. In this paper, we extend the attention mechanism to the task of weakly supervised object localization (WSOL) and propose the dual-attention guided dropblock module (DGDM), which aims at learning the informative and complementary visual patterns for WSOL. This module contains two key components, the channel attention guided dropout (CAGD) and the spatial attention guided dropblock (SAGD). To model channel interdependencies, the CAGD ranks the channel attentions and treats the top-k attentions with the largest magnitudes as the important ones. It also keeps some low-valued elements to increase their value if they become important during training. The SAGD can efficiently remove the most discriminative information by erasing the contiguous regions of feature maps rather than individual pixels. This guides the model to capture the less discriminative parts for classification. Furthermore, it can also distinguish the foreground objects from the background regions to alleviate the attention misdirection. Experimental results demonstrate that the proposed method achieves new state-of-the-art localization performance.

关键词： Location awareness Training Deep learning Adaptation models Visualization pattern recognition Automobiles

来源：评论

学校读者我要写书评

暂无评论

Oracle Character recognition using Unsupervised Discriminative Consistency Network

arXiv

引用

arXiv 2023年

作者： Wang, Mei Deng, Weihong Su, Sen The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China

Ancient history relies on the study of ancient characters. However, real-world scanned oracle characters are difficult to collect and annotate, posing a major obstacle for oracle character recognition (OrCR). Besides, serious abrasion and inter-class similarity also make OrCR more challenging. In this paper, we propose a novel unsupervised domain adaptation method for OrCR, which enables to transfer knowledge from labeled handprinted oracle characters to unlabeled scanned data. We leverage pseudo-labeling to incorporate the semantic information into adaptation and constrain augmentation consistency to make the predictions of scanned samples consistent under different perturbations, leading to the model robustness to abrasion, stain and distortion. Simultaneously, an unsupervised transition loss is proposed to learn more discriminative features on the scanned domain by optimizing both between-class and within-class transition probability. Extensive experiments show that our approach achieves state-of-the-art result on Oracle-241 dataset and substantially outperforms the recently proposed structure-texture separation network by 15.1%. © 2023, CC BY.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Audio Captioning Using Soft and Hard Prompts

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2045-2058页

作者： Yiming Zhang Xuenan Xu Ruoyi Du Haohe Liu Yuan Dong Zheng-Hua Tan Wenwu Wang Zhanyu Ma Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Centre for Vision Speech and Signal Processing University of Surrey Guildford U.K. Department of Electronic Systems Aalborg University Aalborg Denmark

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test set from the same dataset. Such methods have two limitations. First, these methods are often data-hungry and require time-consuming and expensive human annotations to obtain audio-text pairs. Second, these models often suffer from performance degradation in cross-domain scenarios, i.e., when the input audio comes from a different domain than the training set, and this issue has received little attention. To address these issues, we propose a new zero-shot method for audio captioning. Our method is built on the contrastive language-audio pre-training (CLAP) model. During training, the model reconstructs the ground-truth caption using the CLAP text encoder. In the inference stage, the model generates text descriptions from the CLAP audio embeddings of given audio inputs. To enhance the ability of the model in transitioning from text-to-text generation to audio-to-text generation, we propose to use the mixed-augmentations-based soft prompt to learn more robust latent representations, leveraging instance replacement and embedding augmentation. Additionally, we introduce the retrieval-based acoustic-aware hard prompt to improve the cross-domain performance of the model by employing the domain-agnostic label information of sound events. Extensive experiments on AudioCaps and Clotho benchmarks show the effectiveness of our proposed method, which outperforms other zero-shot audio captioning approaches for in-domain scenarios and outperforms the compared methods for cross-domain scenarios, underscoring the generalization ability of our method.

关键词： Training Decoding Semantics Data models Acoustics Electronic mail Benchmark testing Transformers Robustness Perturbation methods

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：