检索结果-内蒙古大学图书馆

Rethinking Distribution Alignment for Inter-class Fairness 1

1st International Conference on Artificial Intelligence Security and Privacy, AIS and P 2023

作者： Ye, Jinhuang Wu, Jiawei Li, Zuoyong Zheng, Xianghan College of Computer and Big Data Fuzhou University Fuzhou350108 China School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen518107 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China

ISBN: (数字)9789819997886

ISBN: (纸本)9789819997879

Semi-supervised learning (SSL) is a successful paradigm that can use unlabelled data to alleviate the labelling cost problem in supervised learning. However, the excellent performance brought by SSL does not transfer well to the task of class imbalance. The reason is that the class bias of pseudo-labelling further misleads the decision boundary. To solve this problem, we propose a new plug-and-play approach to handle the class imbalance problem based on a theoretical extension and analysis of distribution alignment. The method, called Basis Transformation Based Distribution Alignment (BTDA), efficiently aligns class distributions while taking into account inter-class *** implements the basis transformation through a learnable transfer matrix, thereby reducing the performance loss caused by pseudo-labelling biases. Extensive experiments show that our proposed BTDA approach can significantly improve performance in class imbalance tasks in terms of both accuracy and recall metrics when integrated with advanced SSL algorithms. Although the idea of BTDA is not complex, it can show advanced performance on datasets such as CIFAR and SVHN. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation

引用

International Journal of Computer Vision 2025年 1-20页

作者： Xie, Jinheng Deng, Songhe Hou, Xianxu Luo, Zhaochuan Shen, Linlin Huang, Yawen Zheng, Yefeng Shou, Mike Zheng Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Computer Science Wenzhou-Kean University Wenzhou325060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore639798 Singapore School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University Suzhou215400 China Jarvis Research Center Tencent YouTu Lab Shenzhen518703 China

While promising results have been achieved in weakly-supervised semantic segmentation (WSSS), limited supervision from image-level tags inevitably induces discriminative reliance and spurious relations between target classes and background regions. Thus, Class Activation Map (CAM) usually tends to activate discriminative object regions and falsely includes lots of class-related backgrounds. Without pixel-level supervisions, it could be very difficult to enlarge the foreground activation and suppress those false activation of background regions. In this paper, we propose a novel framework of Cross Language Image Matching with Automatic Context Discovery (CLIMS++), based on the recently introduced Contrastive Language-Image Pre-training (CLIP) model, for WSSS. The core idea of our framework is to introduce natural language supervision to activate more complete object regions and suppress class-related background regions in CAM. In particular, we design object, background region, and text label matching losses to guide the model to excite more reasonable object regions of each category. In addition, we propose to automatically find spurious relations between foreground categories and backgrounds, through which a background suppression loss is designed to suppress the activation of class-related backgrounds. The above designs enable the proposed CLIMS++ to generate a more complete and compact activation map for the target objects. Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 datasets show that our CLIMS++ significantly outperforms the previous state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Start-Tv: A Closed-Form Initialization For Total Variation Models

Start-Tv: A Closed-Form Initialization For Total Variation M...

引用

IEEE International Conference on Image processing

作者： Yuanhao Gong Guanghui Yue College of Electronics and Information Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China School of Biomedical Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Although there are many iterative solvers for total variation models, few attention has been paid on the fast and effective approximation to their optimal solutions. In this paper, we propose a closed-form filter that can efficiently and effectively approximate the optimal solution of total variation models. This filter has linear computation complexity $O(n)$ with respect to the total number of pixels and constant computation complexity $O(1)$ with respect to the window radius. Taking such filter as an initialization, our method can significantly accelerate all previous iterative solvers. Numerical experiments confirms that our initialization is roughly equivalent to $\mathbf{5 0}$ iterations in the iterative method but $\mathbf{1 0} \times$ faster. The proposed method can be applied in all total variation models to accelerate the optimization process, such as image smoothing, image reconstruction and optical flow estimation.

关键词： Optical filters Closed-form solutions TV Computational modeling Superresolution Estimation Numerical models

来源：评论

学校读者我要写书评

暂无评论

CRLNet: Cascaded Resolution Learning Network for Natural Scenes Segmentation

引用

IEEE intelligent Systems 2025年

作者： Li, Wei Tian, Shishun Hua, Guoguang Liao, Muxin Zhang, Yuhang Zou, Wenbin Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Advanced Machine Learning and Applications College of Electronics and Information Engineering Shenzhen518060 China Jiangxi Agricultural University School of Computer Science and Engineering Nanchang330045 China

The natural environment presents a multitude of scenes with diverse content, posing challenges for satisfactory segmentation results using existing segmentation networks. In response, we propose a Cascaded Resolution Learning Network (CRLNet) to enhance segmentation performance through global textual embedding and multi-resolution feature learning. The CRLNet constructs a multi-path segmentation system that integrates multi-resolution feature data from different paths, thereby progressively enhancing local feature learning. Two key modules, the Partition-Fusion Channel Attention Module (PFCAM) and the Features Learning Module (FLM), are pivotal components of CRLNet. The PFCAM serves as a computationally efficient channel attention module to mitigate segmentation confusion stemming from similar objects. Meanwhile, the FLM is tailored to learn resolution feature maps from different paths, facilitating the refinement of object representation and enhancing segmentation performance. Extensive experiments conducted on real natural scene datasets demonstrate the superiority of the proposed CRLNet over existing efficient segmentation methods in terms of accuracy. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Charging Schedule Model for Electric Vehicle Battery Swapping Stations with Multiple Battery Types 13

A Dynamic Charging Schedule Model for Electric Vehicle Batte...

引用

13th Asian Control Conference, ASCC 2022

作者： Wu, Jiali Wu, Hao Su, Yong Wang, Na Li, Xia Kwok Hung Pang, Grantham Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen China The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong Hong Kong

ISBN: (纸本)9788993215236

The increasing popularity of electric vehicles (EVs) has posed significant challenges to the existing charging facilities. The existing research works on battery swapping station (BSS) are usually based on the same type of EV battery. This paper introduces a BSS model with multiple battery types for handling the EVs' requests with diverse battery types. To maximize the battery diversity at BSS, we propose a novel objective function with weighted summarized variables and the average charging time of each battery type. We specially designed a dynamic charging schedule strategy to optimize the output power of the charging units at a BSS. Experimental results have been illustrated to verify the effectiveness of the proposed dynamic charging schedule model with multiple battery types. © 2022 ACA.

关键词： Schedules Search methods Optimal scheduling Quality of service Dynamic scheduling Linear programming Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

A Novel Unsupervised Feature Selection based on Correlation Measure between Heterogeneous Features

A Novel Unsupervised Feature Selection based on Correlation ...

引用

Pattern Recognition and Artificial Intelligence (PRAI), International Conference on

作者： Jia-Ming Cai Hong Jia College of Electronics and Information Engineering Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

Most existing feature selection algorithms only focus on a certain type of data, either numerical or categorical. In this paper, we present an unsupervised heterogeneous feature selection method based on a novel feature correlation measurement. Firstly, a unified correlation measuring framework is designed to quantify the correlations between any two features, including features with the same type and different types. Then, a filter-based feature selection algorithm is proposed to remove redundant features and obtain a best feature subset. Various experiments have been conducted on different mixed data sets and the results indicate that the proposed method can obtain better clustering performance with a smaller heterogeneous feature subset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic Segmentation

arXiv

引用

arXiv 2023年

作者： Liao, Muxin Tian, Shishun Zhang, Yuhang Hua, Guoguang Zou, Wenbin Li, Xia Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China

Prototypical contrastive learning (PCL) has been widely used to learn class-wise domain-invariant features recently. These methods are based on the assumption that the prototypes, which are represented as the central value of the same class in a certain domain, are domain-invariant. Since the prototypes of different domains have discrepancies as well, the class-wise domain-invariant features learned from the source domain by PCL need to be aligned with the prototypes of other domains simultaneously. However, the prototypes of the same class in different domains may be different while the prototypes of different classes may be similar, which may affect the learning of class-wise domain-invariant features. Based on these observations, a calibration-based dual prototypical contrastive learning (CDPCL) approach is proposed to reduce the domain discrepancy between the learned class-wise features and the prototypes of different domains for domain generalization semantic segmentation. It contains an uncertainty-guided PCL (UPCL) and a hard-weighted PCL (HPCL). Since the domain discrepancies of the prototypes of different classes may be different, we propose an uncertainty probability matrix to represent the domain discrepancies of the prototypes of all the classes. The UPCL estimates the uncertainty probability matrix to calibrate the weights of the prototypes during the PCL. Moreover, considering that the prototypes of different classes may be similar in some circumstances, which means these prototypes are hard-aligned, the HPCL is proposed to generate a hard-weighted matrix to calibrate the weights of the hard-aligned prototypes during the PCL. Extensive experiments demonstrate that our approach achieves superior performance over current approaches on domain generalization semantic segmentation tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Detection of Photoplethysmography Manipulation in Video Forgery 31

Detection of Photoplethysmography Manipulation in Video Forg...

引用

31st European Signal processing Conference, EUSIPCO 2023

作者： Lin, Yuzhen Li, Bin Maiorana, Emanuele Campisi, Patrizio Guangdong Key Lab of Intelligent Information Processing Shenzhen Key Lab of Media Security Shenzhen University Shenzhen China State Key Laboratory of Radio Frequency Heterogeneous Integration Shenzhen University Shenzhen China Dept. of Industrial Electronic and Mechanical Engineering Roma Tre University Rome Italy

ISBN: (纸本)9789464593600

Recent studies have shown that physiological signals related to blood pressure and heart rate can be estimated in a contactless modality from facial videos using remote photoplethysmography (rPPG). This has paved the way to the development of techniques that can acquire and manipulate the rPPG signals recoverable from facial videos without affecting their visual appearance. The goal of this paper is to analyze the detectability of this new kind of forgery, here referred to as rPPG deepfake videos. Specifically, we propose a two-stream method based on the analysis of rPPG deepfake videos at both spatial and temporal levels. The experimental results obtained from tests performed on samples taken from two distinct databases demonstrate that our method performs better than popular deep learning methods in the rPPG deepfake detection task. © 2023 European Signal processing Conference, EUSIPCO. All rights reserved.

关键词： Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

Single Channel SAR Deception Jamming Recognition Based on Feature Map Learning 5

Single Channel SAR Deception Jamming Recognition Based on Fe...

引用

5th International Conference on information Communication and Signal processing, ICICSP 2022

作者： Liu, Huan Zhao, Bo Huang, Lei Zhang, Liang College of Information Engineering Shenzhen University Shenzhen518060 China Peng Cheng Laboratory Shenzhen518038 China China University of Mining and Technology Xuzhou221116 China Guangdong Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security Shenzhen518060 China

ISBN: (纸本)9781665485890

This paper presents a novel method for SAR deception jamming recognition based on feature map learning. According to different characteristics of the true echo and deceptive jamming in time domain and frequency domain, feature maps are extracted and enhanced from the single channel SAR data through different processing. By organizing different features as different color channels in the imagery, a neural network which is good at target detection and recognition is applied to identify the false target. The proposed method is verified through simulations. © 2022 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

CNN channel pruning via gradient integration and knowledge distillation

CNN channel pruning via gradient integration and knowledge d...

引用

International Conference on Signal processing Proceedings (ICSP)

作者： Suyun Lian Yang Zhao Jiajian Cai Jihong Pei The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

With the advancement of artificial intelligence technology, intelligent applications have permeated all aspects of human life, including automatic driving, intelligent security, and face recognition. Convolutional neural networks (CNNs) are essential models for AI, but their complexity increases with more available data. The complex models are unsuitable for edge devices like wearables and smartphones due to high memory and computational requirements. In this paper, the compact model is achieved by pruning some redundant output channels. To effectively measure the validity of the output channels, this paper proposes a channel pruning algorithm based on gradient integration, which combines the gradient of the channel with the model output and the channel’s values. This pruning could destroy model accuracy, so knowledge distillation is introduced during fine-tuning to leverage the original model’s reasoning ability. Experiments show that our approach improves accuracy by 0.51% while reducing parameters by 30.1% and FLOPs by 26% in the VGG16 model.

关键词： Training Accuracy Computational modeling Signal processing algorithms Signal processing Cognition Convolutional neural networks Security Wearable devices Smart phones

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：