Pattern Recognition Letters最新文献

Attribute alignment networks for generalized zero-shot learning 广义零次学习的属性对齐网络

IF 3.3 3区计算机科学

Pattern Recognition Letters Pub Date : 2025-10-06 DOI: 10.1016/j.patrec.2025.09.010

Nannan Lu, Mingkai Qiu, Jiansheng Qian

{"title":"Attribute alignment networks for generalized zero-shot learning","authors":"Nannan Lu, Mingkai Qiu, Jiansheng Qian","doi":"10.1016/j.patrec.2025.09.010","DOIUrl":"10.1016/j.patrec.2025.09.010","url":null,"abstract":"<div><div>Part-based embedding methods with attention mechanism achieved outstanding results in zero-shot learning (ZSL). However, affected by intra-class variations in the datasets (i.e., different samples of the same class present different attribute characteristics), it is difficult for models based on traditional attention mechanisms to achieve accurate visual-attribute alignment. To tackle this problem, we propose a novel approach to fully utilize attributes information, referred to as attribute alignment networks (AAN). It consists of the attribute alignment (AA) pipeline and the attribute enhancement (AE) module. AA pipeline is a brand-new solution for part-based embedding method, which realizes visual-attribute alignment in both attribute space and attribute semantic space under the supervision of class attribute vectors and attribute word vectors, respectively. AE module employs the Graph Neural Networks (GNNs) to project visual features to the attribute semantic space. Based on the constructed attribute relation graph (ARG) and self-attention mechanism, AE module generates the enhanced representation of attributes to minimize the influence of intra-class variations. Experiments on standard datasets demonstrate that the enhanced attribute representation greatly improves the classification performance. Overall, AAN outperforms the other state-of-the-art performances in ZSL and GZSL tasks.</div></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":"198 ","pages":"Pages 50-56"},"PeriodicalIF":3.3,"publicationDate":"2025-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269730","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

RoNFA: Robust neural field-based approach for few-shot image classification with noisy labels RoNFA：基于鲁棒神经场的带有噪声标签的少量图像分类方法

IF 3.3 3区计算机科学

Pattern Recognition Letters Pub Date : 2025-10-03 DOI: 10.1016/j.patrec.2025.09.009

Nan Xiang , Lifeng Xing , Dequan Jin

{"title":"RoNFA: Robust neural field-based approach for few-shot image classification with noisy labels","authors":"Nan Xiang , Lifeng Xing , Dequan Jin","doi":"10.1016/j.patrec.2025.09.009","DOIUrl":"10.1016/j.patrec.2025.09.009","url":null,"abstract":"<div><div>In few-shot learning (FSL), the labeled samples are scarce. Thus, label errors can significantly reduce classification accuracy. Since label errors are inevitable in realistic learning tasks, improving the robustness of the model in the presence of label errors is critical. This paper proposes a new robust neural field-based image approach (RoNFA) for few-shot image classification with noisy labels. RoNFA consists of two neural fields for feature and category representation. They correspond to the feature space and category set. Each neuron in the field for category representation (FCR) has a receptive field (RF) on the field for feature representation (FFR) centered at the representative neuron for its category generated by soft clustering. In the prediction stage, the range of these receptive fields adapts according to the neuronal activation in FCR to ensure prediction accuracy. These learning strategies provide the proposed model with excellent few-shot learning capability and strong robustness against label noises. The experimental results on real-world FSL datasets with three different types of label noise demonstrate that the proposed method significantly outperforms state-of-the-art FSL methods. Its accuracy obtained in the presence of noisy labels even surpasses the results obtained by state-of-the-art FSL methods trained on clean support sets, indicating its strong robustness against noisy labels.</div></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":"198 ","pages":"Pages 36-42"},"PeriodicalIF":3.3,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269731","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

Large margin classifier with graph-based adaptive regularization 基于图自适应正则化的大边界分类器

IF 3.3 3区计算机科学

Pattern Recognition Letters Pub Date : 2025-09-25 DOI: 10.1016/j.patrec.2025.09.008

Vítor M. Hanriot , Turíbio T. Salis , Luiz C.B. Torres , Frederico Coelho , Antonio P. Braga

引用次数: 0

Multi-period interaction networks for time series forecasting 用于时间序列预测的多周期交互网络

IF 3.3 3区计算机科学

Pattern Recognition Letters Pub Date : 2025-09-22 DOI: 10.1016/j.patrec.2025.09.007

Yuqing Xie, Lujuan Dang, Badong Chen

引用次数: 0

Robust watermarks for audio diffusion models by quadrature amplitude modulation 正交调幅的音频扩散模型鲁棒水印

IF 3.3 3区计算机科学

Pattern Recognition Letters Pub Date : 2025-09-19 DOI: 10.1016/j.patrec.2025.08.023

Kyungryeol Lee , Seongmin Hong , Se Young Chun

{"title":"Robust watermarks for audio diffusion models by quadrature amplitude modulation","authors":"Kyungryeol Lee , Seongmin Hong , Se Young Chun","doi":"10.1016/j.patrec.2025.08.023","DOIUrl":"10.1016/j.patrec.2025.08.023","url":null,"abstract":"<div><div>Generative models enable the creation of high-quality digital content, including images, videos, and audio, making these tools increasingly accessible to users. As their use grows, so does the need for robust copyright protection mechanisms. Existing watermarking methods, primarily post-hoc, can safeguard the copyrights of users but fail to protect service providers, leaving room for intentional misuse, such as erasing watermarks and falsely claiming originality. To address this, previous works proposed integrating watermarks into the noise initialization of diffusion models for image generation, ensuring robustness against attacks like cut-and-paste. However, this approach has not been investigated for audio generation, where the 1D nature of audio data requires fundamentally different techniques. In this paper, we propose a novel barcode-like watermarking method for audio diffusion models, leveraging 4-quadrature amplitude modulation (4-QAM) to embed twice as much information as amplitude modulation methods for existing image generations. Our approach demonstrates significantly improved robustness against attacks, including cut-and-paste, and outperforms state-of-the-art audio watermarking techniques in preserving information and ensuring copyright protection for both users and service providers.</div></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":"198 ","pages":"Pages 22-28"},"PeriodicalIF":3.3,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145121301","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

From open-vocabulary to vocabulary-free semantic segmentation 从开放词汇到无词汇的语义切分

IF 3.3 3区计算机科学

Pattern Recognition Letters Pub Date : 2025-09-17 DOI: 10.1016/j.patrec.2025.08.025

Klara Reichard , Giulia Rizzoli , Stefano Gasperini , Lukas Hoyer , Pietro Zanuttigh , Nassir Navab , Federico Tombari

{"title":"From open-vocabulary to vocabulary-free semantic segmentation","authors":"Klara Reichard , Giulia Rizzoli , Stefano Gasperini , Lukas Hoyer , Pietro Zanuttigh , Nassir Navab , Federico Tombari","doi":"10.1016/j.patrec.2025.08.025","DOIUrl":"10.1016/j.patrec.2025.08.025","url":null,"abstract":"<div><div>Open-vocabulary semantic segmentation enables models to identify novel object categories beyond their training data. While this flexibility represents a significant advancement, current approaches still rely on manually specified class names as input, creating an inherent bottleneck in real-world applications. This work proposes a Vocabulary-Free Semantic Segmentation pipeline, eliminating the need for predefined class vocabularies. Specifically, we address the chicken-and-egg problem where users need knowledge of all potential objects within a scene to identify them, yet the purpose of segmentation is often to discover these objects. The proposed approach leverages Vision–Language Models to automatically recognize objects and generate appropriate class names, aiming to solve the challenge of class specification and naming quality. Through extensive experiments on several public datasets, we highlight the crucial role of the text encoder in model performance, particularly when the image text classes are paired with generated descriptions. Despite the challenges introduced by the sensitivity of the segmentation text encoder to false negatives within the class tagging process, which adds complexity to the task, we demonstrate that our fully automated pipeline significantly enhances vocabulary-free segmentation accuracy across diverse real-world scenarios. Code is available at <span><span>https://github.com/klarareichard/open-vocab2free-seg</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":"198 ","pages":"Pages 14-21"},"PeriodicalIF":3.3,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145121300","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

Orthogonal nonnegative matrix factorization with the Kullback–Leibler divergence 具有Kullback-Leibler散度的正交非负矩阵分解

IF 3.3 3区计算机科学

Pattern Recognition Letters Pub Date : 2025-09-15 DOI: 10.1016/j.patrec.2025.08.012

Jean Pacifique Nkurunziza , Fulgence Nahayo , Nicolas Gillis

引用次数: 0

TSMR-Net: a two-stage multimodal medical image registration method via pseudo-image generation and deformable registration TSMR-Net：一种通过伪图像生成和变形配准的两阶段多模态医学图像配准方法

IF 3.3 3区计算机科学

Pattern Recognition Letters Pub Date : 2025-09-14 DOI: 10.1016/j.patrec.2025.09.006

Dongxue Li , Xin Yang , Songyu Chen , Liwei Deng , Qi Lan , Sijuan Huang , Jing Wang

{"title":"TSMR-Net: a two-stage multimodal medical image registration method via pseudo-image generation and deformable registration","authors":"Dongxue Li , Xin Yang , Songyu Chen , Liwei Deng , Qi Lan , Sijuan Huang , Jing Wang","doi":"10.1016/j.patrec.2025.09.006","DOIUrl":"10.1016/j.patrec.2025.09.006","url":null,"abstract":"<div><div>Multimodal medical image registration is critical for accurate diagnosis, treatment planning, and surgical guidance. However, differences in imaging mechanisms cause substantial appearance discrepancies between modalities, hindering effective feature extraction and similarity measurement. We propose TSMR-Net, a two-stage multimodal registration framework. In the first stage, an Intensity Distribution Regression module nonlinearly transforms the fixed image into a modality-consistent generated fixed-like image, reducing inter-modality appearance gaps. In the second stage, a deformable registration network aligns the generated fixed-like and moving images using a unimodal similarity metric. The architecture incorporates a parallel downsampling module for multi-scale spatial feature capture and residual skip connections with a 3D channel interaction module to enhance feature propagation. Experiments on IXI and BraTS2023 datasets show that TSMR-Net outperforms state-of-the-art methods in alignment precision, structural consistency, and deformation stability. These findings validate the two-stage strategy’s effectiveness in bridging modality gaps and improving registration accuracy. TSMR-Net provides a scalable, robust solution for diverse multimodal registration tasks with strong potential for clinical application.</div></div>","PeriodicalId":54638,"journal":{"name":"Pattern Recognition Letters","volume":"197 ","pages":"Pages 359-367"},"PeriodicalIF":3.3,"publicationDate":"2025-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145104698","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

Which images can be effectively learnt from self-supervised learning? 哪些图像可以从自监督学习中有效学习？

IF 3.3 3区计算机科学

Pattern Recognition Letters Pub Date : 2025-09-13 DOI: 10.1016/j.patrec.2025.09.003

Michalis Lazarou , Sata Atito , Muhammad Awais , Josef Kittler

引用次数: 0

TransStyle: Transformer-based StyleGAN for image inversion and editing TransStyle：用于图像反转和编辑的基于transformer的StyleGAN

IF 3.3 3区计算机科学

Pattern Recognition Letters Pub Date : 2025-09-10 DOI: 10.1016/j.patrec.2025.09.002

Yingchun Guo, Xueqi Lv, Gang Yan, Shu Chen, Shi Di

引用次数: 0