Pattern Recognition Letters最新文献_第10页

Conditional Information Gain Trellis 条件信息增益结构

IF 3.9 3区计算机科学

Pattern Recognition Letters Pub Date : 2024-06-22 DOI: 10.1016/j.patrec.2024.06.018

Ufuk Can Bicici , Tuna Han Salih Meral , Lale Akarun

{"title":"Conditional Information Gain Trellis","authors":"Ufuk Can Bicici , Tuna Han Salih Meral , Lale Akarun","doi":"10.1016/j.patrec.2024.06.018","DOIUrl":"https://doi.org/10.1016/j.patrec.2024.06.018","url":null,"abstract":"<div><p>Conditional computing processes an input using only part of the neural network’s computational units. Learning to execute parts of a deep convolutional network by routing individual samples has several advantages: This can facilitate the interpretability of the model, reduce the model complexity, and reduce the computational burden during training and inference. Furthermore, if similar classes are routed to the same path, that part of the network learns to discriminate between finer differences and better classification accuracies can be attained with fewer parameters. Recently, several papers have exploited this idea to select a particular child of a node in a tree-shaped network or to skip parts of a network. In this work, we follow a Trellis-based approach for generating specific execution paths in a deep convolutional neural network. We have designed routing mechanisms that use differentiable information gain-based cost functions to determine which subset of features in a convolutional layer will be executed. We call our method Conditional Information Gain Trellis (CIGT). We show that our conditional execution mechanism achieves comparable or better model performance compared to unconditional baselines, using only a fraction of the computational resources. We provide our code and model checkpoints used in the paper at: <span>https://github.com/ufukcbicici/cigt/tree/prl/prl_scripts</span><svg><path></path></svg>.</p></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2024-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141543126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

End-to-end latent fingerprint enhancement using multi-scale Generative Adversarial Network 利用多尺度生成式对抗网络进行端到端潜指纹增强

IF 3.9 3区计算机科学

Pattern Recognition Letters Pub Date : 2024-06-22 DOI: 10.1016/j.patrec.2024.06.022

Pramukha R.N. , Akhila P. , Shashidhar G. Koolagudi

引用次数: 0

Learning to learn point signature for 3D shape geometry 学会学习三维形状几何的点特征

IF 3.9 3区计算机科学

Pattern Recognition Letters Pub Date : 2024-06-22 DOI: 10.1016/j.patrec.2024.06.021

Hao Huang , Lingjing Wang , Xiang Li , Shuaihang Yuan , Congcong Wen , Yu Hao , Yi Fang

{"title":"Learning to learn point signature for 3D shape geometry","authors":"Hao Huang , Lingjing Wang , Xiang Li , Shuaihang Yuan , Congcong Wen , Yu Hao , Yi Fang","doi":"10.1016/j.patrec.2024.06.021","DOIUrl":"https://doi.org/10.1016/j.patrec.2024.06.021","url":null,"abstract":"<div><p>Point signature is a representation that describes the structural geometry of a point within a neighborhood in 3D shapes. Conventional approaches apply a weight-sharing network, <em>e.g.</em>, Graph Neural Network (GNN), to all neighborhoods of all points to directly generate point signatures and gain the generalization ability of the network by extensive training over amounts of samples from scratch. However, such approaches lack the flexibility to rapidly adapt to unseen neighborhood structures and thus cannot generalize well to new point sets. In this paper, we propose a novel meta-learning 3D point signature model, <em>3D <strong>me</strong>ta <strong>p</strong>oint <strong>s</strong>ignature (MEPS) network</em>, which is capable of learning robust 3D point signatures. Regarding each point signature learning process as a task, our method obtains an optimized model over the best performance on the distribution of all tasks, generating reliable signatures for new tasks, <em>i.e.</em>, signatures of unseen point neighborhoods. Specifically, our MEPS consists of two modules: a <em>base signature learner</em> and a <em>meta signature learner</em>. During training, a <em>base-learner</em> is trained to perform specific signature learning tasks. Meanwhile, a <em>meta-learner</em> is trained to update the base-learner with optimal parameters. During testing, the meta-learner learned with the distribution of all tasks can adaptively change the base-learner parameters to accommodate unseen local neighborhoods. We evaluate our MEPS model on 3D shape correspondence and segmentation. Experimental results demonstrate that our method not only gains significant improvements over the baseline model to achieve state-of-the-art performance, but also is capable of handling unseen 3D geometry. Our implementation is available at <span>https://github.com/hhuang-code/MEPS</span><svg><path></path></svg>.</p></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2024-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141481668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Latent spectral regularization for continual learning 持续学习的潜谱正则化

IF 3.9 3区计算机科学

Pattern Recognition Letters Pub Date : 2024-06-22 DOI: 10.1016/j.patrec.2024.06.020

Emanuele Frascaroli , Riccardo Benaglia , Matteo Boschini , Luca Moschella , Cosimo Fiorini , Emanuele Rodolà , Simone Calderara

{"title":"Latent spectral regularization for continual learning","authors":"Emanuele Frascaroli , Riccardo Benaglia , Matteo Boschini , Luca Moschella , Cosimo Fiorini , Emanuele Rodolà , Simone Calderara","doi":"10.1016/j.patrec.2024.06.020","DOIUrl":"https://doi.org/10.1016/j.patrec.2024.06.020","url":null,"abstract":"<div><p>While biological intelligence grows organically as new knowledge is gathered throughout life, Artificial Neural Networks forget catastrophically whenever they face a changing training data distribution. Rehearsal-based Continual Learning (CL) approaches have been established as a versatile and reliable solution to overcome this limitation; however, sudden input disruptions and memory constraints are known to alter the consistency of their predictions. We study this phenomenon by investigating the geometric characteristics of the learner’s latent space and find that replayed data points of different classes increasingly mix up, interfering with classification. Hence, we propose a geometric regularizer that enforces weak requirements on the Laplacian spectrum of the latent space, promoting a partitioning behavior. Our proposal, called Continual Spectral Regularizer for Incremental Learning (CaSpeR-IL), can be easily combined with any rehearsal-based CL approach and improves the performance of SOTA methods on standard benchmarks.</p></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2024-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0167865524001909/pdfft?md5=843aa8ad438387d8ae33f617b9e9e4d3&pid=1-s2.0-S0167865524001909-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141482529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An efficient ensemble explainable AI (XAI) approach for morphed face detection 用于变形人脸检测的高效集合可解释人工智能（XAI）方法

IF 3.9 3区计算机科学

Pattern Recognition Letters Pub Date : 2024-06-22 DOI: 10.1016/j.patrec.2024.06.014

Rudresh Dwivedi, Pranay Kothari, Deepak Chopra, Manjot Singh, Ritesh Kumar

{"title":"An efficient ensemble explainable AI (XAI) approach for morphed face detection","authors":"Rudresh Dwivedi, Pranay Kothari, Deepak Chopra, Manjot Singh, Ritesh Kumar","doi":"10.1016/j.patrec.2024.06.014","DOIUrl":"https://doi.org/10.1016/j.patrec.2024.06.014","url":null,"abstract":"<div><p>Numerous deep neural convolutional architectures have been proposed in literature for face Morphing Attack Detection (MADs) to prevent such attacks and lessen the risks associated with them. Although, deep learning models achieved optimal results in terms of performance, it is difficult to understand and analyze these networks since they are black box/opaque in nature. As a consequence, incorrect judgments may be made. There is, however, a dearth of literature that explains decision-making methods of black box deep learning models for biometric Presentation Attack Detection (PADs) or MADs that can aid the biometric community to have trust in deep learning-based biometric systems for identification and authentication in various security applications such as border control, criminal database establishment etc. In this work, we present a novel visual explanation approach named Ensemble XAI integrating Saliency maps, Class Activation Maps (CAM) and Gradient-CAM (Grad-CAM) to provide a more comprehensive visual explanation for a deep learning prognostic model (EfficientNet-B1) that we have employed to predict whether the input presented to a biometric authentication system is morphed or genuine. The experimentations have been performed on three publicly available datasets namely Face Research Lab London (FRLL) dataset, Wide Multi-Channel Presentation Attack (WMCA) dataset, and Makeup Induced Face Spoofing (MIFS) dataset. The experimental evaluations affirms that the resultant visual explanations highlight more fine-grained details of image features/areas focused by EfficientNet-B1 to reach decisions along with appropriate reasoning.</p></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2024-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141543130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Self-supervised learning with automatic data augmentation for enhancing representation 利用自动数据扩增技术进行自我监督学习，增强表征能力

IF 3.9 3区计算机科学

Pattern Recognition Letters Pub Date : 2024-06-22 DOI: 10.1016/j.patrec.2024.06.012

Chanjong Park , Eunwoo Kim

{"title":"Self-supervised learning with automatic data augmentation for enhancing representation","authors":"Chanjong Park , Eunwoo Kim","doi":"10.1016/j.patrec.2024.06.012","DOIUrl":"https://doi.org/10.1016/j.patrec.2024.06.012","url":null,"abstract":"<div><p>Self-supervised learning has become an increasingly popular method for learning effective representations from unlabeled data. One prominent approach in self-supervised learning is contrastive learning, which trains models to distinguish between similar and dissimilar sample pairs by pulling similar pairs closer and pushing dissimilar pairs farther apart. The key to the success of contrastive learning lies in the quality of the data augmentation, which increases the diversity of the data and helps the model learn more powerful and generalizable representations. While many studies have emphasized the importance of data augmentation, however, most of them rely on human-crafted augmentation strategies. In this paper, we propose a novel method, <strong>S</strong>elf <strong>A</strong>ugmentation on <strong>C</strong>ontrastive <strong>L</strong>earning with <strong>Cl</strong>ustering (SACL), searching for the optimal data augmentation policy automatically using Bayesian optimization and clustering. The proposed approach overcomes the limitations of relying on domain knowledge and avoids the high costs associated with manually designing data augmentation rules. It automatically captures informative and useful features within the data by exploring augmentation policies. We demonstrate that the proposed method surpasses existing approaches that rely on manually designed augmentation rules. Our experiments show SACL outperforms manual strategies, achieving a performance improvement of 1.68% and 1.57% over MoCo v2 on the CIFAR10 and SVHN datasets, respectively.</p></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2024-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141481669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Discovering the signal subgraph: An iterative screening approach on graphs 发现信号子图：图上的迭代筛选方法

IF 3.9 3区计算机科学

Pattern Recognition Letters Pub Date : 2024-06-18 DOI: 10.1016/j.patrec.2024.06.011

Cencheng Shen , Shangsi Wang , Alexandra Badea , Carey E. Priebe , Joshua T. Vogelstein

{"title":"Discovering the signal subgraph: An iterative screening approach on graphs","authors":"Cencheng Shen , Shangsi Wang , Alexandra Badea , Carey E. Priebe , Joshua T. Vogelstein","doi":"10.1016/j.patrec.2024.06.011","DOIUrl":"https://doi.org/10.1016/j.patrec.2024.06.011","url":null,"abstract":"<div><p>Supervised learning on graphs is a challenging task due to the high dimensionality and inherent structural dependencies in the data, where each edge depends on a pair of vertices. Existing conventional methods are designed for standard Euclidean data and do not account for the structural information inherent in graphs. In this paper, we propose an iterative vertex screening method to achieve dimension reduction across multiple graph datasets with matched vertex sets and associated graph attributes. Our method aims to identify a signal subgraph to provide a more concise representation of the full graphs, potentially benefiting subsequent vertex classification tasks. The method screens the rows and columns of the adjacency matrix concurrently and stops when the resulting distance correlation is maximized. We establish the theoretical foundation of our method by proving that it estimates the true signal subgraph with high probability. Additionally, we establish the convergence rate of classification error under the Erdos-Renyi random graph model and prove that the subsequent classification can be asymptotically optimal, outperforming the entire graph under high-dimensional conditions. Our method is evaluated on various simulated datasets and real-world human and murine graphs derived from functional and structural magnetic resonance images. The results demonstrate its excellent performance in estimating the ground-truth signal subgraph and achieving superior classification accuracy.</p></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141482527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Zigzag persistence for image processing: New software and applications 用于图像处理的 "之 "字形持久性：新软件和应用

IF 3.9 3区计算机科学

Pattern Recognition Letters Pub Date : 2024-06-15 DOI: 10.1016/j.patrec.2024.06.010

Jose Divasón , Ana Romero , Pilar Santolaria , Jesús L. Yániz

引用次数: 0

Student State-aware knowledge tracing based on attention mechanism: A cognitive theory view 基于注意力机制的学生状态感知知识追踪：认知理论观点

IF 3.9 3区计算机科学

Pattern Recognition Letters Pub Date : 2024-06-14 DOI: 10.1016/j.patrec.2024.06.009

Liyin Qian, Kaiwen Zheng, Luqi Wang, Sheng Li

{"title":"Student State-aware knowledge tracing based on attention mechanism: A cognitive theory view","authors":"Liyin Qian, Kaiwen Zheng, Luqi Wang, Sheng Li","doi":"10.1016/j.patrec.2024.06.009","DOIUrl":"10.1016/j.patrec.2024.06.009","url":null,"abstract":"<div><p>Knowledge tracing evaluates students’ knowledge state and predicts future performance by analyzing their past interactions. Recent research integrates features of learning activities into knowledge tracing to enhance interpretability. Ausubel’s cognitive theory underscores the significance of cognitive accumulation in learning, perceiving it as a process in which new content is linked and integrated with students’ existing knowledge. Yet, current studies often overlook this cognitive property and its impact on performance prediction. Therefore, we propose an attention-based knowledge tracing model, named Student State-aware knowledge tracing (SSKT). To align with this cognitive process, we incorporate suitable Query, Key, and Value objects into the attention mechanism, effectively modeling how students extract, integrate, and apply information from their existing knowledge. Meanwhile, traditional RNN-based models encounter the issue of losing early learning data due to gradient vanishing in long sequences. Our hybrid model, which combines LSTM and Transformer, efficiently extracts early learning information using an attention mechanism. Extensive experiments on real-world datasets validate the effectiveness and interpretability of SSKT.</p></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141394035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Query-guided generalizable medical image segmentation 查询引导的可通用医学图像分割

IF 5.1 3区计算机科学

Pattern Recognition Letters Pub Date : 2024-06-13 DOI: 10.1016/j.patrec.2024.06.005

Zhiyi Yang , Zhou Zhao , Yuliang Gu , Yongchao Xu

引用次数: 0