检索结果-内蒙古大学图书馆

Mind the Gap: Open Set Domain Adaptation via Mutual-to-Separate Framework

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第6期34卷 4159-4174页

作者： Chang, Dongliang Sain, Aneeshan Ma, Zhanyu Song, Yi-Zhe Wang, Ruiping Guo, Jun Beijing Univ Posts & Telecommun Sch Artificial Intelligence Pattern Recognit & Intelligent Syst Lab Beijing 100876 Peoples R China Univ Surrey Ctr Vis Speech & Signal Proc Guildford GU2 7XH England Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China

Unsupervised domain adaptation aims to leverage labeled data from a source domain to learn a classifier for an unlabeled target domain. Amongst its many variants, open set domain adaptation (OSDA) is perhaps the most challenging one, as it further assumes the presence of unknown classes in the target domain. In this paper, we study OSDA with a particular focus on enriching its ability to traverse across larger domain gaps, and we show that existing state-of-the-art methods suffer a considerable performance drop in the presence of larger domain gaps, especially on a new dataset (PACS) that we re-purposed for OSDA. Exploring this is pivotal for OSDA as with increasing domain shift, identifying unknown samples in the target domain becomes harder for the model, thus making negative transfer between source and target domains more challenging. Accordingly, we propose a Mutual-to-Separate (MTS) framework to address the larger domain gaps. Essentially we design two networks - (a) Sample Separation Network (SSN): which is trained to learn a hyperplane for separating unknown samples from known ones, and (b) Distribution Matching Network (DMN): which is trained to maximise domain confusion between source and target domains without unknown samples under the guidance of the SSN. The key insight lies in how we exploit the mutually beneficial information between these two networks. On closer observation, we see that SSN can reveal which samples in the target domain belong to the unknown class by instance weighting whereas, DMN pushes apart the samples that most likely belong to the unknown class in the target domain, which in turn reduces the difficulty of SSN in identifying unknown samples. It follows that (a) and (b) will mutually supervise each other and alternate until convergence, which can better align the source and target domains in the shared label space. Extensive experiments on five datasets (Office-31, Office-Home, PACS, visDA, and mini _DomainNet) demonstrate the effi

关键词： Picture archiving and communication systems Training Task analysis labeling Adaptation models visualization Information exchange Domain adaptation open set mutual learning transfer learning

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Mutual Information-Based Multilabel Feature Selection With label Dependency and Streaming labels

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2023年第1期31卷 77-91页

作者： Liu, Jinghua Lin, Yaojin Ding, Weiping Zhang, Hongbo Du, Jixiang Huaqiao Univ Sch Comp Sci & Technol Xiamen 361021 Peoples R China Minnan Normal Univ Key Lab Data Sci & Intelligence Applicat Zhangzhou 363000 Peoples R China Nantong Univ Sch Informat Sci & Technol Nantong 226019 Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Fujian Key Lab Big Data Intelligence & Secur Xiamen 361021 Peoples R China

Multilabel feature selection (MFS) has received widespread attention in various big data applications. However, most of the existing methods either explicitly or implicitly assume that all labels are given in advance before feature selection starts;or that all labels are independent. In fact, in many practical applications, the available labels usually arrive dynamically, and they may be interdependent with each other. Moreover, labels may be generated dynamically in a minibatch manner, which makes it more difficult to explore label dependency. In this article, we propose a novel fuzzy mutual information-based multilabel feature selection approach MSDS, which is able to solve single streaming label, minibatch streaming labels, and exploit label dependency simultaneously. In specific, we first promote fuzzy mutual information to be suitable for multilabel learning. This model can effectively consider the relationship between two labels, and has good applicability for measuring the relationship between multiple labels. Then, we analyze feature relevance and feature redundancy based on the combination of label dependency and streaming labels, which helps to facilitate the selection of high-quality feature subsets. Finally, a feature conversion is designed to fuse the representative features of new arrival streaming labels. comprehensive experiments on twelve multilabel datasets clearly reveal the superiority of the proposed method against two streaming labels based algorithms and five state-of-the-art static label space based algorithms.

关键词： Correlation Feature extraction Redundancy Task analysis Social networking (online) Optimization Electronic mail Feature selection fuzzy mutual information label dependency multilabel learning streaming labels

来源：评论

学校读者我要写书评

暂无评论

Image inpainting via spatial projections

引用

pattern recognitION 2023年 133卷

作者： Phutke, Shruti S. Murala, Subrahmanyam Indian Inst Technol Ropar Comp Vis & Pattern Recognit Lab Ropar India

Image inpainting is now-a-days sought after due to its wide variety of applications in the reconstruction of the corrupted image, occlusion removal, reflection removal, etc. Existing image inpainting approaches utilize different types of attention mechanisms to inpaint the image and produce visibly admirable re-sults. These methods are more concerned at weighing the feature maps of the hole region with some weight from the non-hole region. But, due to the lack of spatial contextual correlation in the atten-tion maps, the inpainted image may suffer from the inconsistencies among hole and non-hole regions. Transformer-based inpainting methods give significant results by capturing the relationship between the patches with a compromise of high computational complexity. In this context, we propose a novel spa-tial projection layer (SPL) without any attention mechanism to project the spatial contextual information in the hole region from non-hole regions for producing a spatially plausible inpainted image. The SPL is proposed mainly to focus on the non-hole spatial information in the high-level feature maps for fill-ing the hole regions efficiently. Also, while training the network, we propose the use of edge loss with a Canny edge operator for image inpainting to focus on the relevant edges instead of noise contents. Analysis with the extensive experiments, ablation, and user study on the proposed architecture demon-strates the superiority over existing state-of-the-art methods for image inpainting. The code is available at: https://***/shrutiphutke/spatial _ projection _ inpainting .(c) 2022 Elsevier Ltd. All rights reserved.

关键词： Spatial projections Inpainting Object removal

来源：评论

学校读者我要写书评

暂无评论

SiamCCF: Siamese visual tracking via cross-layer calibration fusion

引用

IET compUTER visION 2023年第8期17卷 869-882页

作者： Chen, Si Huang, Huang Zhu, Shunzhi Xu, Huarong He, Yifan Wang, Da-Han Xiamen Univ Technol Sch Comp & Informat Engn Fujian Key Lab Pattern Recognit & Image Understand Xiamen Peoples R China Reconova Technol Co Ltd Xiamen Peoples R China

Siamese networks have attracted wide attention in visual tracking due to their competitive accuracy and speed. However, the existing Siamese trackers usually leverage a fixed linear aggregation of feature maps, which does not effectively fuse the different layers of features with attention. Besides, most of Siamese trackers calculate the similarity between the template and the search region through a cross-correlation operation between the features of the last blocks from the two branches, which might introduce the redundant noise information. In order to solve these problems, this study proposes a novel Siamese visual tracking method via cross-layer calibration fusion, termed SiamCCF. An attention-based feature fusion module is employed using local attention and non-local attention to fuse the features from the deep and shallow layers, so as to capture both local details and high-level semantic information. Moreover, a cross-layer calibration module can use the fused features to calibrate the features of the last network blocks and build the cross-layer long-range spatial and inter-channel dependencies around each spatial location. Extensive experiments demonstrate that the proposed method has achieved competitive tracking performance compared with state-of-the-art trackers on challenging benchmarks, including OTB100, OTB2013, UAV123, UAV20L, and LaSOT.

关键词： computer vision object tracking

来源：评论

学校读者我要写书评

暂无评论

A new deep model for family and non-family photo identification

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第2期81卷 1765-1785页

作者： Karnik, Tapan Shivakumara, Palaiahnakote Chowdhury, Pinaki Nath Pal, Umapada Lu, Tong Anuar, Nor Badrul Indian Stat Inst Comp Vis & Pattern Recognit Unit Kolkata India Univ Malaya Fac Comp Sci & Informat Technol Kuala Lumpur Malaysia Nanjing Univ Natl Key Lab Novel Software Technol Nanjing Peoples R China

Human trafficking is a global issue of the world and the problems related to human trafficking remain unsolved. This paper presents a new method for the identification of photos of different types of families and non-families such that the method can assist investigation team to find a solution to such issue. We believe that parts of human beings are the main resources for representing family and non-family photos. Based on this intuition, we propose to segment hair, head, cloth, torso, and skin regions from each human in input photos by exploring a self-correlation for human parsing method. This step results in region of interest (ROI). Motivated by ability of deep learning models in solving complex issues and special property of MobileNet, which is light weight model, we further explore MobileNetv2 for the identification of photos of different families and non-families by considering ROI as the input. For the experiment of this work, we consider a dataset of ten classes, which include five family classes, namely, Couple, Nuclear Family, Multi-Cultural Family, Father-Child, Mother-Child and five more non-family classes, namely, Male Friends, Female Friends, Mixed Friends, Male Celebrity, Female Celebrity. The results of the proposed method are demonstrated by testing on our dataset of family and non-family photos classification. comparative results with the existing methods show that our proposed method outperforms existing methods in terms of classification rate and F-Score.

关键词： Human trafficking Kinship verification Human parsing Deep learning Multimodal approach Family and non-family photos

来源：评论

学校读者我要写书评

暂无评论

Dual-graph with non-convex sparse regularization for multi-label feature selection

引用

APPLIED INTELLIGENCE 2023年第18期53卷 21227-21247页

作者： Sun, Zhenzhen Xie, Hao Liu, Jinghua Gou, Jin Yu, Yuanlong HuaQiao Univ Coll Comp Sci & Technol Jimei Ave Xiamen 361021 Fujian Peoples R China HuaQiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Jimei Ave Xiamen 361021 Fujian Peoples R China Fuzhou Univ Coll Comp & Data Sci Wulong Jiangbei Ave Fuzhou 350108 Fujian Peoples R China

As for single-label learning, feature selection has become a crucial data pre-processing tool for multi-label learning due to its ability to reduce the feature dimensionality to mitigate the influence of "the curse of dimensionality". In recent years, the multi-label feature selection (MFS) methods based on manifold learning and sparse regression have confirmed their superiority and gained more and more attention than other methods. However, most of these methods only consider exploiting the geometric structure distributed in the data manifold but ignore the geometric structure distributed in the feature manifold, resulting in incomplete information about the learned manifold. Aiming to simultaneously exploit the geometric information of data and feature spaces for feature selection, this paper proposes a novel MFS method named dual-graph based multi-label feature selection (DGMFS). In the framework of DGMFS, two nearest neighbor graphs are constructed to form a dual-graph regularization to explore the geometric structures of both the data manifold and the feature manifold simultaneously. Then, we combined the dual-graph regularization with a non-convex sparse regularization l(2,1 - 2)-norm to obtain a more sparse solution for the weight matrix, which can better deal with the redundancy features. Finally, we adopt the EM strategy to design an iterative updating optimization algorithm for DGMFS and provide the convergence analysis of the optimization algorithm. Extensive experimental results on ten benchmark multi-label data sets have shown that DGMFS is more effective than several state-of-the-art MFS methods.

关键词： Feature selection Multi-label learning Dual graph Non-convex sparse regularization

来源：评论

学校读者我要写书评

暂无评论

Consistency Regularization for Deep Face Anti-Spoofing

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2023年 18卷 1127-1140页

作者： Wang, Zezheng Yu, Zitong Wang, Xun Qin, Yunxiao Li, Jiahong Zhao, Chenxu Liu, Xin Lei, Zhen Kuaishou Technol MMU Beijing Peoples R China Great Bay Univ Guangzhou Peoples R China Commun Univ China State Key Lab Media Convergence & Commun Beijing Peoples R China SailYond Technol Beijing Peoples R China Lappeenranta Lahti Univ Technol LUT Comp Vis & Pattern Recognit Lab Lappeenranta Finland Chinese Acad Sci CASIA Inst Automation Ctr Biometr & Secur Res CBSR Natl Lab Pattern Recognit NLPR Beijing Peoples R China

Face anti-spoofing (FAS) plays a crucial role in securing face recognition systems. Empirically, given an image, a model with more consistent output on different views (i.e., augmentations) of this image usually performs better. Motivated by this exciting observation, we conjecture that encouraging feature consistency of different views may be a promising way to boost FAS models. In this paper, we explore this way thoroughly by enhancing both Embedding-level and Prediction-level Consistency Regularization (EPCR) in FAS. Specifically, at the embedding level, we design a dense similarity loss to maximize the similarities between all positions of two intermediate feature maps in a self-supervised fashion;while at the prediction level, we optimize the mean square error between the predictions of two views. Notably, our EPCR is free of annotations and can directly integrate into semi-supervised learning schemes. Considering different application scenarios, we further design five diverse semi-supervised protocols to measure semi-supervised FAS techniques. We conduct extensive experiments to show that EPCR can significantly improve the performance of several supervised and semi-supervised tasks on benchmark datasets.

关键词： Face recognition Faces Task analysis Training Benchmark testing Supervised learning Protocols Face anti-spoofing consistency regularization semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

GridIIS: Grid Based Interactive Image Segmentation 6th

GridIIS: Grid Based Interactive Image Segmentation

引用

6th Chinese Conference on pattern recognition and computer vision (PRCV)

作者： Zhu, Pengqi Wang, Da-Han Zhu, Shunzhi Xiaman Univ Technol Sch Comp & Informat Engn Xiamen Peoples R China Fujian Key Lab Pattern Recognit & Image Understan Xiamen Peoples R China

ISBN: (纸本)9789819985517;9789819985524

Interactive segmentation enables users to specify the object of interest (OOI) via various interaction strategies to obtain accurate segmentation results. An ideal interactive method should efficiently and accurately express users' segmentation intentions. However, the existing methods can only use a single interactive mode, ignoring the differences in scale and shape between OOIs, resulting in an inflexibility labeling process. In this paper, we propose a grid-based interactive image segmentation method (GridIIS). Specifically, GridIIS overlays grids on the image, and users can specify the location and shape of the OOI by selecting the grid areas as the interactive guidance. Users can choose the appropriate grid selection method and size considering the OOI's scale, shape, and boundary clarity to obtain guidance. We accordingly propose a novel grid sampling strategy, that considers the OOI's scale and shapes to adaptively estimate the grid size and area. Experiments on several datasets from different domains (street views, medical images, scene texts, etc.) show that our method achieves superior performance with fewer interaction rounds and exhibits strong generalization ability in cross-domain datasets.

关键词： Interactive segmentation Grid-based interactive

来源：评论

学校读者我要写书评

暂无评论

Multi-view anomaly detection via hybrid instance-neighborhood aligning and cross-view reasoning

引用

MULTIMEDIA SYSTEMS 2024年第6期30卷 1-14页

作者： Tian, Luo Peng, Shu-Juan Liu, Xin Chen, Yewang Cao, Jianjia Huaqiao Univ Dept Comp Sci 668 Jimei St Xiamen 361021 Fujian Peoples R China Xiamen Key Lab Comp Vis & Pattern Recognit 668 Jimei St Xiamen 361021 Fujian Peoples R China Xiamen Wangsu Ltd Co Artificial Intelligence Res Inst 64 Chengyi North St Xiamen 361000 Fujian Peoples R China Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen 361021 Peoples R China

Multi-view anomaly detection aims to identify anomalous instances whose patterns are disparate across different views, and existing works usually project the multi-view data into a common subspace for abnormal instance identification. Nevertheless, these methods often fail to explicitly excavate the inter-view dependency and discrepancy among the multi-view data, which are of crucial importance to detect inconsistent patterns across different views interactively. To address this problem, we propose an efficient multi-view anomaly detection method via instance-neighborhood aligning and cross-view reasoning, which can well parse the inter-view dependency and discrepancy to detect various kinds of anomalous multi-view instances. To be specific, we first utilize the view-specific encoder to project the original data into the latent feature space, in which a novel instance-neighborhood aligning scheme is seamlessly embedded to preserve the consistent neighborhood structures of multiple views and maximize the consistency for the semantically relevant instances, which indirectly enhances the inter-view dependencies. Meanwhile, a cross-view reasoning module is efficiently designed to explore the inter-view dependencies and discrepancies, which can explicitly boost the inter-view correlations and differences to reason the inconsistent view patterns. Through the joint exploitation of the view-specific reconstruction loss, instance-neighborhood aligning loss, and cross-view reasoning loss, different kinds of anomalous multi-view instances can be well detected more reliably. Extensive experiments evaluated on benchmark datasets, quantitatively and qualitatively, verify the advantages of the proposed multi-view anomaly detection framework and show its substantial improvements over the state of the arts. The code is available at: https://***/tl-git320/INA-CR.

关键词： Multi-view learning Anomaly detection Cross-view reasoning Inter-view dependency and discrepancy Instance-neighborhood aligning

来源：评论

学校读者我要写书评

暂无评论

Dynamic behavior and modulation instability for a generalized nonlinear Schrödinger equation with nonlocal nonlinearity

引用

PHYSICA SCRIPTA 2025年第1期100卷

作者： Zhang, Kun Cao, Jiangping Lyu, Jingjing Chengdu Univ Coll Comp Sci Chengdu 610106 Peoples R China Chengdu Univ Key Lab Pattern Recognit & Intelligent Informat Pr Chengdu 610106 Peoples R China Natl Inst Measurement & Testing Technol Chengdu 610021 Peoples R China

This paper focus on the generalized nonlinear Schr & ouml;dinger equation with triple refractive index and nonlocal nonlinearity, which is used to describe the evolution state of optical solitons in fiber optic propagation. Firstly, the complex exponential traveling wave transformation and substitution method are utilized to convert the equation into two-dimensional planar dynamic system, and then by phase portrait the developmental patterns of solutions are qualitatively analyzing. Meanwhile, the evolution of solutions under different disturbances in the system is discussed. Qualitative analysis of the system are displayed through Poincar & eacute;section and sensitivity analysis. Finally, the instability of the system is modulated by using linear stability analysis method, and the corresponding conditions for steady-state solutions and the gain spectrum function are obtained.

关键词： nonlocal nonlinearity chaotic behavior dispersion effect modulation instability

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：