检索结果-内蒙古大学图书馆

Differentially private ADMM algorithms for machine learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xu, Tao Shang, Fanhua Liu, Yuanyuan Liu, Hongying Shen, Longjie Gong, Maoguo Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Electronic Engineering Xidian University China

In this paper, we study efficient differentially private alternating direction methods of multipliers (ADMM) via gradient perturbation for many machine learning problems. For smooth convex loss functions with (non)-smooth regularization, we propose the first differentially private ADMM (DP-ADMM) algorithm with performance guarantee of (∊, δ)-differential privacy ((∊, δ)-DP). From the viewpoint of theoretical analysis, we use the Gaussian mechanism and the conversion relationship between Rényi Differential Privacy (RDP) and DP to perform a comprehensive privacy analysis for our algorithm. Then we establish a new criterion to prove the convergence of the proposed algorithms including DP-ADMM. We also give the utility analysis of our DP-ADMM. Moreover, we propose an accelerated DP-ADMM (DP-AccADMM) with the Nesterov’s acceleration technique. Finally, we conduct numerical experiments on many real-world datasets to show the privacy-utility tradeoff of the two proposed algorithms, and all the comparative analysis shows that DP-AccADMM converges faster and has a better utility than DP-ADMM, when the privacy budget ∊ is larger than a threshold. Copyright © 2020, The Authors. All rights reserved.

关键词： Budget control

Diff-Reg: Diffusion Model in Doubly Stochastic Matrix Space for Registration Problem

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Qianliang Jiang, Haobo Luo, Lei Li, Jun Ding, Yaqing Xie, Jin Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Intelligence Science and Technology Nanjing University Suzhou China Visual Recognition Group Faculty of Electrical Engineering Czech Technical University in Prague Prague Czech Republic National University of Singapore Singapore

Establishing reliable correspondences is essential for 3D and 2D-3D registration tasks. Existing methods commonly leverage geometric or semantic point features to generate potential correspondences. However, these features may face challenges such as large deformation, scale inconsistency, and ambiguous matching problems (e.g., symmetry). Additionally, many previous methods, which rely on single-pass prediction, may struggle with local minima in complex scenarios. To mitigate these challenges, we introduce a diffusion matching model for robust correspondence construction. Our approach treats correspondence estimation as a denoising diffusion process within the doubly stochastic matrix space, which gradually denoises (refines) a doubly stochastic matching matrix to the ground-truth one for high-quality correspondence estimation. It involves a forward diffusion process that gradually introduces Gaussian noise into the ground truth matching matrix and a reverse denoising process that iteratively refines the noisy one. In particular, we deploy a lightweight denoising strategy during the inference phase. Specifically, once points/image features are extracted and fixed, we utilize them to conduct multiple-pass denoising predictions in the reverse sampling process. Evaluation of our method on both 3D and 2D-3D registration tasks confirms its effectiveness. The code is available at https://***/wuqianliang/Diff-Reg. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

Texture and wavelet based PCANet (TW-PCANet) for infants' facial expression recognition 2019

学校读者我要写书评

暂无评论

Texture and wavelet based PCANet (TW-PCANet) for infants' fa...

2019 International Conference on Artificial Intelligence and Computer Science, AICS 2019

作者： Shen, Fang Liu, Jing Wu, Peng Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi'an China

ISBN: (纸本)9781450371506

The babyhood is a very important stage in the human growth process. Thus learning the facial expression characteristics of infants is of great significance to nursing care for infants. Infants' faces are significantly different from adults' faces, like eyebrows, eyes, nose, cheeks, skin texture, etc. Therefore, the facial expression recognition models trained on adults' facial expression database cannot be directly applied to infants' facial expression recognition. There are dozens of facial expression databases for adults' facial expression analysis, but there is no database composed by various infants' facial expressions. Hence we first collect candid images of infants' facial expression, which includes six obvious expressions of infants, namely crying, curious, happy, sleeping, wronged, neutral. Then the texture and wavelet based PCANet (TW-PCANet) is proposed to fully extract the features of infants' facial expressions. The proposed method first handles original input color images by local binary patterns (LBP) and Gabor wavelet, then the processed images are put into the PCANet to get the final class. The experimental results show that the proposed method can achieve higher recognition rate obtained by PCANet, LBP and Gabor wavelet. © 2019 Association for Computing Machinery.

关键词： Local binary pattern

Generalization-aware Remote Sensing Change Detection via Domain-agnostic Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zang, Qi Wang, Shuang Zhao, Dong Quan, Dou Hu, Yang Jiao, Licheng Yang, Zhi Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University Xi’an710071 China DFH Satellite Co. Ltd CAST Beijing100080 China

Change detection has essential significance for the region’s development, in which pseudo-changes between bitemporal images induced by imaging environmental factors are key challenges. Existing transformation-based methods regard pseudo-changes as a kind of style shift and alleviate it by transforming bitemporal images into the same style using generative adversarial networks (GANs). However, their efforts are limited by two drawbacks: 1) Transformed images suffer from distortion that reduces feature discrimination. 2) Alignment hampers the model from learning domain-agnostic representations that degrades performance on scenes with domain shifts from the training data. Therefore, oriented from pseudo-changes caused by style differences, we present a generalizable domain-agnostic difference learning network (DonaNet). For the drawback 1), we argue for local-level statistics as style proxies to assist against domain shifts. For the drawback 2), DonaNet learns domain-agnostic representations by removing domain-specific style of encoded features and highlighting the class characteristics of objects. In the removal, we propose a domain difference removal module to reduce feature variance while preserving discriminative properties and propose its enhanced version to provide possibilities for eliminating more style by decorrelating the correlation between features. In the highlighting, we propose a cross-temporal generalization learning strategy to imitate latent domain shifts, thus enabling the model to extract feature representations more robust to shifts actively. Extensive experiments conducted on three public datasets demonstrate that DonaNet outperforms existing state-of-the-art methods with a smaller model size and is more robust to domain shift. © 2025, CC BY.

关键词： Change detection

SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label image Classification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Lei Zhan, Yibing Ma, Leilei Tao, Dapeng Ding, Liang Gong, Chen The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing210094 China The JD Explore Academy Beijing100000 China The School of Computer Science and Technology Anhui University Anhui Heifei230601 China The FIST LAB School of Information Science and Engineering Yunnan University Yunnan Kunming650091 China

Recently, Mix-style data augmentation methods (e.g., Mixup and CutMix) have shown promising performance in various visual tasks. However, these methods are primarily designed for single-label images, ignoring the considerable discrepancies between single- and multi-label images, i.e., a multi-label image involves multiple co-occurred categories and fickle object scales. On the other hand, previous multi-label image classification (MLIC) methods tend to design elaborate models, bringing expensive computation. In this paper, we introduce a simple but effective augmentation strategy for multi-label image classification, namely SpliceMix. The "splice" in our method is two-fold: 1) Each mixed image is a splice of several downsampled images in the form of a grid, where the semantics of images attending to mixing are blended without object deficiencies for alleviating co-occurred bias;2) We splice mixed images and the original mini-batch to form a new SpliceMixed mini-batch, which allows an image with different scales to contribute to training together. Furthermore, such splice in our SpliceMixed mini-batch enables interactions between mixed images and original regular images. We also offer a simple and non-parametric extension based on consistency learning (SpliceMix-CL) to show the flexible extensibility of our SpliceMix. Extensive experiments on various tasks demonstrate that only using SpliceMix with a baseline model (e.g., ResNet) achieves better performance than state-of-the-art methods. Moreover, the generalizability of our SpliceMix is further validated by the improvements in current MLIC methods when married with our SpliceMix. The code is available at https://***/zuiran/SpliceMix. Copyright © 2023, The Authors. All rights reserved.

关键词： image classification

Hyperspectral image Classification Based on Semi-Supervised Dual-Branch Convolutional Autoencoder with Self-Attention

学校读者我要写书评

暂无评论

Hyperspectral Image Classification Based on Semi-Supervised ...

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Jie Feng Zhanwei Ye Di Li Yuping Liang Xu Tang Xiangrong Zhang Ministry of Education Key Laboratory of Intelligent Perception and Image Understanding Xidian University Xi'an China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Deep learning method shows its powerful classification performance with sufficient available data. However, the labeled data is limited in hyperspectral images (HSIs). Semi-supervised algorithms have unique advantages on dealing with this problem. Therefore, a semi-supervised convolutional neural network is proposed in this paper. It consists of two branches, which use limited labeled samples and a large number of unlabeled samples, respectively. The first branch includes an encoder-decoder model to extract contextual information of unlabeled samples. The other one uses the similar construction except extra classification layers to extract discriminative features of labeled samples. In order to fuse contextual and discriminative information, we cascade the features of low-level layers from different branches. Furthermore, self-attention is added to the first branch, which focuses more on the global information for classification. The experiment results show that the proposed model provides a competitive result compared with state-of-the-art methods.

关键词： Feature extraction Hyperspectral imaging Training Fuses Data mining Convolutional neural networks Unsupervised learning

Small Object Detection in Optical Remote Sensing Video with Motion Guided R-CNN

学校读者我要写书评

暂无评论

Small Object Detection in Optical Remote Sensing Video with ...

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Jie Feng Yuping Liang Zhanwei Ye Xiande Wu Dening Zeng Xiangrong Zhang Xu Tang Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi'an China

ISBN: (数字)9781728163741

ISBN: (纸本)9781728163758

Deep learning (DL) based object detection methods have been making great achievements for natural images, which guides the vehicle detection of optical remote sensing videos (ORSV). Compared with natural images, objects in ORSV are smaller and blurrier, and most of vehicles are crowded. Thus, it is difficult for DL to detect these small objects only using the single-frame image. To address this problem, a motion guided R-CNN (MG-RCNN) is proposed. In MG-RCNN, motion information from consecutive frames is extracted by the mean differencing method and merged into apparent information to obtain motion-related discriminative features. Then, high-quality proposals are generated on the feature maps by mini-region proposal network (MRPN). For small targets, an improved loss function is defined by incorporating smooth factor, which makes the regression of shapes more stable. Experiments on ORSV demonstrate the proposed method shows superior detection performance over state-of-the-art deep learning methods.

关键词： Object detection Proposals Feature extraction Detectors Remote sensing Data mining Video sequences

A study on small magnitude seismic phase identification using 1D deep residual neural network

学校读者我要写书评

暂无评论

Artificial Intelligence in Geosciences 2022年第1期3卷 115-122页

作者： Wei Li Megha Chakraborty Yu Sha Kai Zhou Johannes Faber Georg Rümpker Horst Stöcker Nishtha Srivastava Frankfurt Institute for Advanced Studies Frankfurt am Main60438Germany Institute of Geosciences Goethe-University FrankfurtFrankfurt am Main60438Germany Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education Academy of Advanced Interdisciplinary ResearchXidian UniversityXian710071China Xidian-FIAS international Joint Research Center Giersch Science CenterFrankfurt am Main60438Germany Institut für Theoretische Physik Goethe Universität FrankfurtFrankfurt am Main60438Germany GSI Helmholtzzentrum für Schwerionenforschung GmbH Darmstadt64291Germany

Reliable seismic phase identification is often challenging especially in the circumstances of low-magnitude events or poor signal-to-noise *** improved seismometers and better global coverage,a sharp increase in the volume of recorded seismic data has been *** makes handling seismic data rather daunting by using traditional approaches and therefore fuels the need for more robust and reliable *** this study,we develop 1D deep Residual Neural Network(ResNet),for tackling the problem of seismic signal detection and phase *** method is trained and tested on the dataset recorded by the Southern California Seismic *** demonstrate that the proposed method can achieve robust performance for the detection of seismic signals and the identification of seismic *** to previously proposed deep learning methods,the introduced framework achieves around 4%improvement in earthquake detection and a slightly better performance in seismic phase identification on the dataset recorded by Southern California Earthquake Data *** model generalizability is also tested further on the STanford EArthquake *** addition,the experimental result on the same subset of the STanford EArthquake Dataset,when masked by different noise levels,demonstrates the model’s robustness in identifying the seismic phases of small magnitude.

关键词： Deep learning Residual neural network Earthquake detection Seismic phase identification

Grouped Adaptive Loss Weighting for Person Search

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tian, Yanling Chen, Di Liu, Yunan Zhang, Shanshan Yang, Jian School of Artificial Intelligence Dalian Maritime University China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

Person search is an integrated task of multiple sub-tasks such as foreground/background classification, bounding box regression and person re-identification. Therefore, person search is a typical multi-task learning problem, especially when solved in an end-to-end manner. Recently, some works enhance person search features by exploiting various auxiliary information, e.g. person joint key-points, body part position, attributes, etc., which brings in more tasks and further complexifies a person search model. The inconsistent convergence rate of each task could potentially harm the model optimization. A straightforward solution is to manually assign different weights to different tasks, compensating for the diverse convergence rates. However, given the special case of person search, i.e. with a large number of tasks, it is impractical to weight the tasks manually. To this end, we propose a Grouped Adaptive Loss Weighting (GALW) method which adjusts the weight of each task automatically and dynamically. Specifically, we group tasks according to their convergence rates. Tasks within the same group share the same learnable weight, which is dynamically assigned by considering the loss uncertainty. Experimental results on two typical benchmarks, CUHK-SYSU and PRW, demonstrate the effectiveness of our method. © 2022, CC BY.

关键词： Learning systems