-
Discriminative Regularized Input Manifold for multilayer perceptron Pattern Recogn. (IF 8.0) Pub Date : 2024-03-11 Rahul Mondal, Tandra Pal, Prasenjit Dey
Multilayer perceptron (MLP) fails to discriminate the ambiguous inputs belonging to the overlapping regions of multiple classes, resulting in misclassification. To classify the input samples accurately according to their classes, removing the ambiguity that occurred due to the sharing of common input space is important. In this article, a novel neural network framework, called Discriminative Regularized
-
Dog Identification Based on Textural Features and Spatial Relation of Noseprint Pattern Recogn. (IF 8.0) Pub Date : 2024-03-10 Yung-Kuan Chan, Chuen-Horng Lin, Ching-Lin Wang, Keng-Chang Tu, Shu-Chun Yang, Meng-Hsiun Tsai, Shyr-Shen Yu
This study proposes dog identification technology based on dog noseprints, which are equivalent to human fingerprints and possess unique characteristics. The aim is to utilize this technology for identifying and managing stray animals. The study presents three processing stages. In the first stage, YOLOv3 detects the dog's nose and nostril regions. The second stage involves enhancing the image's contrast
-
Parameter-free ensemble clustering with dynamic weighting mechanism Pattern Recogn. (IF 8.0) Pub Date : 2024-03-10 Fangyuan Xie, Feiping Nie, Weizhong Yu, Xuelong Li
Ensemble clustering (EC) gains more and more attention because it can improve the effectiveness and robustness of single clustering methods. A popular ensemble approach is to construct a co-association matrix which represents the possibility that the sample pair is divided into different clusters by base clusterings. Then, some single clustering methods could be performed on it. However, this approach
-
Rigid pairwise 3D point cloud registration: A survey Pattern Recogn. (IF 8.0) Pub Date : 2024-03-07 Mengjin Lyu, Jie Yang, Zhiquan Qi, Ruijie Xu, Jiabin Liu
Over the past years, 3D point cloud registration has attracted unprecedented attention. Researchers develop various approaches to tackle the challenging task, such as optimization-based and deep learning-based methods. To systematically sort out the relevant literature and follow the state-of-the-art solutions, this paper conducts a thorough survey. We propose a novel taxonomy dubbed Intermediates
-
LATFormer: Locality-Aware Point-View Fusion Transformer for 3D shape recognition Pattern Recogn. (IF 8.0) Pub Date : 2024-03-07 Xinwei He, Silin Cheng, Dingkang Liang, Song Bai, Xi Wang, Yingying Zhu
Recently, 3D shape understanding has achieved significant progress due to the advances of deep learning models on various data formats like images, voxels, and point clouds. Among them, point clouds and multi-view images are two complementary modalities of 3D objects, and learning representations by fusing both of them has been proven to be fairly effective. While prior works typically focus on exploiting
-
ISP-IRLNet: Joint optimization of interpretable sampler and implicit regularization learning network for accerlerated MRI Pattern Recogn. (IF 8.0) Pub Date : 2024-03-07 Xing Li, Yan Yang, Hairong Zheng, Zongben Xu
Compressed Sensing Magnetic Resonance Imaging (CS-MRI) was proposed to accelerate data acquisition and reconstruct MR images from under-sampled data in -space. However, the traditional approaches design the sampling patterns separately from the reconstruction process, which often leads to suboptimal reconstruction performance. To address this issue, we propose a joint optimization model dubbed as ISP-IRLNet
-
Multi-label feature selection via latent representation learning and dynamic graph constraints Pattern Recogn. (IF 8.0) Pub Date : 2024-03-07 Yao Zhang, Wei Huo, Jun Tang
As an effective method to deal with the curse of dimensionality, multi-label feature selection aims to select the most representative subset of features by eliminating unfavorable features. Although great progress has been made in this field, how to mine adequate supervisory information from multi-label data remains a key challenge. Compared to the latent information of instances, the latent information
-
AG-Meta: Adaptive graph meta-learning via representation consistency over local subgraphs Pattern Recogn. (IF 8.0) Pub Date : 2024-03-07 Yi Wang, Changqin Huang, Ming Li, Qionghao Huang, Xuemei Wu, Jia Wu
Graph meta-learning has recently received significantly increased attention by virtue of its potential to extract common and transferable knowledge from learning different tasks on a graph. Existing methods for graph meta-learning usually leverage local subgraphs to transfer subgraph-specific information. However, they inherently face the challenge of imbalanced subgraphs due to inconsistent node density
-
UGNet: Uncertainty aware geometry enhanced networks for stereo matching Pattern Recogn. (IF 8.0) Pub Date : 2024-03-06 Zhengkai Qi, Junkang Zhang, Faming Fang, Tingting Wang, Guixu Zhang
Stereo matching is a fundamental research area in the field of computer vision. In recent years, iterative methods based on Gated Recurrent Units (GRUs) have showcased remarkable achievements in this domain. Despite their high accuracy, these methods suffer from notable limitations such as a reliance on a large number of iterations and a tendency to lose high-frequency details. To address these issues
-
Prompting large language model with context and pre-answer for knowledge-based VQA Pattern Recogn. (IF 8.0) Pub Date : 2024-03-06 Zhongjian Hu, Peng Yang, Yuanshuang Jiang, Zijian Bai
Existing studies apply Large Language Model (LLM) to knowledge-based Visual Question Answering (VQA) with encouraging results. Due to the insufficient input information, the previous methods still have shortcomings in constructing the prompt for LLM, and cannot fully activate the capacity of LLM. In addition, previous works adopt GPT-3 for inference, which has expensive costs. In this paper, we propose
-
Deep Joint Semantic Adaptation Network for Multi-source Unsupervised Domain Adaptation Pattern Recogn. (IF 8.0) Pub Date : 2024-03-05 Zhiming Cheng, Shuai Wang, Defu Yang, Jie Qi, Mang Xiao, Chenggang Yan
Multi-source Unsupervised Domain Adaptation (MUDA) transfers knowledge learned from multiple labeled source domains to an unlabeled target domain by minimizing the domain shift between multiple source domains and the target domain. Recent studies on MUDA have focused on aligning the distribution of each pair of source and target domains in separate feature spaces to reduce their domain shift. However
-
Deterministic attribute selection for isolation forest Pattern Recogn. (IF 8.0) Pub Date : 2024-03-05 Łukasz Gałka, Paweł Karczmarek
[Display omitted]
-
Neural Knitworks: Patched neural implicit representation networks Pattern Recogn. (IF 8.0) Pub Date : 2024-03-04 Mikolaj Czerkawski, Javier Cardona, Robert Atkinson, Craig Michie, Ivan Andonovic, Carmine Clemente, Christos Tachtatzis
Optimizing images as output of a neural network has been shown to introduce a powerful prior for image inverse tasks, capable of producing solutions of reasonable quality in a fully internal learning context, where no external datasets are involved. Two potential technical approaches involve fitting a coordinate-based Multilayer Perceptron (MLP), or a Convolutional Neural Network to produce the result
-
Noise level estimation using locality preserving natural image statistics Pattern Recogn. (IF 8.0) Pub Date : 2024-03-03 Gitam Shikkenawis, Suman K. Mitra, Ashutosh Saxena
Natural images are known to have certain regular statistical properties. These properties get modified under any artificial change or distortion in natural images. Most common form of image degradation occurs in the form of noise. The amount of degradation in noisy images is measured by estimating the noise level. Many image processing applications such as denoising, restoration, segmentation, compression
-
Uncertainty-driven active developmental learning Pattern Recogn. (IF 8.0) Pub Date : 2024-03-02 Qinghua Hu, Luona Ji, Yu Wang, Shuai Zhao, Zhibin Lin
Existing machine learning models can well handle common classes but struggle to detect unfamiliar or unknown classes due to environmental variations. To address this challenge, we propose a new task called active developmental learning (ADL), which empowers models to actively determine what to learn in the open world, thereby progressively enhancing the capability of detecting unfamiliar and unknown
-
Decoupled representation for multi-view learning Pattern Recogn. (IF 8.0) Pub Date : 2024-03-02 Shiding Sun, Bo Wang, Yingjie Tian
Learning multi-view data is a central topic for advanced deep model applications. Existing efforts mainly focus on exploring shared information to maximize the consensus among all the views. However, after reasonably discarding superfluous task-irrelevant noise, the view-specific information is equally essential to downstream tasks. In this paper, we propose to decouple the multi-view representation
-
Multi-task hierarchical convolutional network for visual-semantic cross-modal retrieval Pattern Recogn. (IF 8.0) Pub Date : 2024-03-02 Zhong Ji, Zhigang Lin, Haoran Wang, Yanwei Pang, Xuelong Li
Bridging visual and textual representations plays a central role in delving into multimedia data understanding. The main challenge arises from that images and texts exist in heterogeneous spaces, leading to the difficulty to preserve the semantic consistency between both modalities. To narrow the modality gap, most recent methods resort to extra object detectors or parsers to obtain the hierarchical
-
Query-centric distance modulator for few-shot classification Pattern Recogn. (IF 8.0) Pub Date : 2024-03-02 Wenxiao Wu, Yuanjie Shao, Changxin Gao, Jing-Hao Xue, Nong Sang
Few-shot classification (FSC) is a highly challenging task, as only a small number of labeled samples are available when identifying new categories. Distance metric learning-based methods have emerged as a prominent approach to FSC, which typically use a distance function to measure the difference between query and support samples for identifying the class membership of the query sample. However, these
-
Deep anomaly detection on set data: Survey and comparison Pattern Recogn. (IF 8.0) Pub Date : 2024-03-02 Michaela Mašková, Matěj Zorek, Tomáš Pevný, Václav Šmídl
Detecting anomalous samples in set data is a problem attracting increased interest due to novel modalities, such as point-cloud data produced by lidars. Novel methods including those based on deep neural networks are often tuned for a single purpose prohibiting intuition of how relevant they are for another purpose or application domains. The aim of this survey is to: (i) review elementary concepts
-
Flexible image denoising model with multi-layer conditional feature modulation Pattern Recogn. (IF 8.0) Pub Date : 2024-03-01 Jiazhi Du, Xin Qiao, Zifei Yan, Hongzhi Zhang, Wangmeng Zuo
For flexible non-blind image denoising, existing deep networks usually concatenate noisy image and noise level map as the input for handling various noise levels with a single model. However, in this kind of solution, the noise variance (i.e., noise level) is only deployed to modulate the first layer of convolution feature with channel-wise shifting, which is limited in balancing noise removal and
-
Data filtering for efficient adversarial training Pattern Recogn. (IF 8.0) Pub Date : 2024-03-01 Erh-Chung Chen, Che-Rung Lee
Adversarial training has been considered to be one of the most effective strategies to defend against adversarial attacks. Most existing adversarial training methods have shown a trade-off between training cost and robustness. This paper explores a new optimization direction from training data to reduce the computational cost of adversarial training without scarifying robustness. First, we show that
-
Spectral clustering with linear embedding: A discrete clustering method for large-scale data Pattern Recogn. (IF 8.0) Pub Date : 2024-03-01 Chenhui Gao, Wenzhi Chen, Feiping Nie, Weizhong Yu, Zonghui Wang
In recent decades, spectral clustering has found widespread applications in various real-world scenarios, showcasing its effectiveness. Traditional spectral clustering typically follows a two-step procedure to address the optimization problem. However, this approach may result in substantial information loss and performance decline. Furthermore, the eigenvalue decomposition, a key step in spectral
-
Bibimbap : Pre-trained models ensemble for Domain Generalization Pattern Recogn. (IF 8.0) Pub Date : 2024-03-01 Jinho Kang, Taero Kim, Yewon Kim, Changdae Oh, Jiyoung Jung, Rakwoo Chang, Kyungwoo Song
This paper addresses a machine learning problem often challenged by differences in the distributions of training and real-world data. We propose a framework that addresses the problem of underfitting in the ensembling method using pre-trained models and improves the performance and robustness of deep learning models through ensemble diversity. For the naive weight ensembling framework, we discovered
-
Embrace sustainable AI: Dynamic data subset selection for image classification Pattern Recogn. (IF 8.0) Pub Date : 2024-02-29 Zimo Yin, Jian Pu, Ru Wan, Xiangyang Xue
Data selection is commonly used to reduce costs and energy usage by training on a subset of available data. However, determining the appropriate subset size requires extensive dataset knowledge and experimentation, limiting transferability. Varying the validation set also produces unstable results and wastes computational resources. In this paper, we propose a data selection method for dynamically
-
Test-time adaptation for 6D pose tracking Pattern Recogn. (IF 8.0) Pub Date : 2024-02-29 Long Tian, Changjae Oh, Andrea Cavallaro
We propose a test-time adaptation for 6D object pose tracking that learns to adapt a pre-trained model to track the 6D pose of novel objects. We consider the problem of 6D object pose tracking as a 3D keypoint detection and matching task and present a model that extracts 3D keypoints. Given an RGB-D image and the mask of a target object for each frame, the proposed model consists of the self- and cross-attention
-
A randomized algorithm for clustering discrete sequences Pattern Recogn. (IF 8.0) Pub Date : 2024-02-29 Mudi Jiang, Lianyu Hu, Xin Han, Yong Zhou, Zengyou He
Cluster analysis is one of the most important research issues in data mining and machine learning. To date, numerous clustering algorithms have been proposed to tackle the fixed-length vector data. In many real applications, we need to detect clusters from a set of discrete sequences in which each sequence is an ordered list of items. Due to the sequential and discrete nature, the discrete sequence
-
Graph Convolutional Network with elastic topology Pattern Recogn. (IF 8.0) Pub Date : 2024-02-28 Zhihao Wu, Zhaoliang Chen, Shide Du, Sujia Huang, Shiping Wang
Graph Convolutional Network (GCN) has drawn widespread attention in data mining on graphs due to its outstanding performance and rigor theoretical guarantee. However, some recent studies have revealed that GCN-based methods may mine latent information insufficiently owing to the underutilization of the feature space. Besides, the unlearnable topology also significantly imperils the performance of GCN-based
-
Cross-lingual few-shot sign language recognition Pattern Recogn. (IF 8.0) Pub Date : 2024-02-28 Yunus Can Bilge, Nazli Ikizler-Cinbis, Ramazan Gokberk Cinbis
There are over 150 sign languages worldwide, each with numerous local variants and thousands of signs. However, collecting annotated data for each sign language to train a model is a laborious and expert-dependent task. To address this issue, this paper introduces the problem of few-shot sign language recognition (FSSLR) in a cross-lingual setting. The central motivation is to be able to recognize
-
Survey of spectral clustering based on graph theory Pattern Recogn. (IF 8.0) Pub Date : 2024-02-28 Ling Ding, Chao Li, Di Jin, Shifei Ding
Spectral clustering converts the data clustering problem to the graph cut problem. It is based on graph theory. Due to the reliable theoretical basis and good clustering performance, spectral clustering has been successfully applied in many fields. Although spectral clustering has many advantages, it faces the challenges of high time and space complexity when dealing with large scale complex data.
-
Global feature-based multimodal semantic segmentation Pattern Recogn. (IF 8.0) Pub Date : 2024-02-28 Suining Gao, Xiubin Yang, Li Jiang, Zongqiang Fu, Jiamin Du
Incorporating complementary modality into RGB branch can significantly improve the effectiveness of semantic segmentation. However, fusion between the two modalities faces huge challenge due to the difference of their optical dimensions. Existed fusion methods can't keep a balance between performance and efficiency in aggregating detailed features. To address this problem, we propose a global feature-based
-
Learning spatial-spectral dual adaptive graph embedding for multispectral and hyperspectral image fusion Pattern Recogn. (IF 8.0) Pub Date : 2024-02-28 Xuquan Wang, Feng Zhang, Kai Zhang, Weijie Wang, Xiong Dun, Jiande Sun
Fusion of high spatial resolution multispectral (HR MS) and low spatial resolution hyperspectral (LR HS) images has become a significant way to produce high spatial resolution hyperspectral (HR HS) images. Though many methods have exploited the spatial nonlocal similarity (SNS) and spectral band correlation (SBC) in the HR HS image, it is difficult to model the priors explicitly because the HR HS image
-
Medical image segmentation based on dynamic positioning and region-aware attention Pattern Recogn. (IF 8.0) Pub Date : 2024-02-28 Zhongmiao Huang, Shuli Cheng, Liejun Wang
Transformer has already proven its ability to model long-distance dependencies. However, medical images have strong local structures. Directly using Transformer to extract features would not only contain redundant information increasing the computational effort, but also be detrimental to extracting local details. Given these issues, we propose a network based on dynamic positioning and region-aware
-
Efficient high-resolution template matching with vector quantized nearest neighbour fields Pattern Recogn. (IF 8.0) Pub Date : 2024-02-28 Ankit Gupta, Ida-Maria Sintorn
Template matching is a fundamental problem in computer vision with applications in fields including object detection, image registration, and object tracking. Current methods rely on nearest-neighbour (NN) matching, where the query feature space is converted to NN space by representing each query pixel with its NN in the template. NN-based methods have been shown to perform better in occlusions, appearance
-
BALQUE: Batch active learning by querying unstable examples with calibrated confidence Pattern Recogn. (IF 8.0) Pub Date : 2024-02-27 Yincheng Han, Dajiang Liu, Jiaxing Shang, Linjiang Zheng, Jiang Zhong, Weiwei Cao, Hong Sun, Wu Xie
Active learning alleviates labeling costs by selecting and labeling the most informative examples from an unlabeled pool. However, most existing active learning approaches estimate informativeness with uncalibrated confidence, resulting in unreliable informativeness estimation. These approaches generally ignored two significant issues caused by uncalibrated confidence methods. Firstly, the average
-
Global and local multi-modal feature mutual learning for retinal vessel segmentation Pattern Recogn. (IF 8.0) Pub Date : 2024-02-27 Xin Zhao, Jing Zhang, Qiaozhe Li, Tengfei Zhao, Yi Li, Zifeng Wu
Research on optical coherence tomography angiography (OCTA) images has received extensive attention in recent years since it provides more detailed information about retinal structures. The automatic segmentation of retinal vessel (RV) has become one of the key issues in the quantification of retinal indicators. To this end, there are various methods proposed with cutting-edge designs and techniques
-
Introspective GAN: Learning to grow a GAN for incremental generation and classification Pattern Recogn. (IF 8.0) Pub Date : 2024-02-27 Chen He, Ruiping Wang, Shiguang Shan, Xilin Chen
Lifelong learning, the ability to continually learn new concepts throughout our life, is a hallmark of human intelligence. Generally, humans learn a new concept by knowing and , which are correlated. Those two ways can be characterized by generation and classification in machine learning respectively. In this paper, we carefully design a dynamically growing GAN called that can perform incremental generation
-
Adaptive and fuzzy locality discriminant analysis for dimensionality reduction Pattern Recogn. (IF 8.0) Pub Date : 2024-02-27 Jingyu Wang, Hengheng Yin, Feiping Nie, Xuelong Li
Linear discriminant analysis (LDA) uses labeled samples for acquiring a discriminant projection direction, by which data of different categories are separated into distinct groups in a lower-dimensional subspace. In response to the issue that LDA lacks robustness to non-Gaussian data with rich local information, improvements on LDA explore the subspace manifold structure by building a fully connected
-
Integrated convolutional neural networks for joint super-resolution and classification of radar images Pattern Recogn. (IF 8.0) Pub Date : 2024-02-24 Rahul Sharma, Bhabesh Deka, Vincent Fusco, Okan Yurduseven
Deep learning techniques have been widely used for two-dimensional (2D) and three-dimensional (3D) computer vision problems, such as object detection, super-resolution (SR) and classification to name a few. Radar images suffer from poor resolution as compared to optical images, hence developing a high-accuracy model to solve computer vision problems, such as a classifier, is a challenge. This is because
-
Wavelet-based Auto-Encoder for simultaneous haze and rain removal from images Pattern Recogn. (IF 8.0) Pub Date : 2024-02-24 Asfak Ali, Ram Sarkar, Sheli Sinha Chaudhuri
Noise introduced due to weather can reduce the efficiency of computer vision applications as the visibility of the objects in images is greatly affected. Haze and rain are the most common weather conditions seen in nature. However, most of the algorithms found in the literature apply rain and haze removal approaches separately. To this end, in this paper, we propose a novel Wavelet-based deep Auto-encoder
-
An approach for handwritten Chinese text recognition unifying character segmentation and recognition Pattern Recogn. (IF 8.0) Pub Date : 2024-02-24 Ming-Ming Yu, Heng Zhang, Fei Yin, Cheng-Lin Liu
Text line recognition methods can be categorized into explicit segmentation based and implicit segmentation based ones. Explicit segmentation based methods require character-level annotation during training, while implicit segmentation based methods, trained on line-level annotated data, face alignment drift challenges. Though some methods have been proposed to address these challenges using weakly
-
A thorough experimental comparison of multilabel methods for classification performance Pattern Recogn. (IF 8.0) Pub Date : 2024-02-23 Nicolás E. García-Pedrajas, José M. Cuevas-Muñoz, Gonzalo Cerruela-García, Aida de Haro-García
Multilabel classification as a data mining task has recently attracted increasing interest from researchers. Many current data mining applications address problems with instances that belong to more than one class. These problems require the development of new, efficient methods. Advantageously using the correlation among different labels can provide better performance than methods that manage each
-
Camera-aware cluster-instance joint online learning for unsupervised person re-identification Pattern Recogn. (IF 8.0) Pub Date : 2024-02-23 Zhaoru Chen, Zheyi Fan, Yiyu Chen, Yixuan Zhu
Unsupervised person re-identification (re-ID) aims at learning discriminative feature representations for person retrieval without any annotations. Pseudo-label-based methods that iteratively perform pseudo-label generation and model training are currently the most popular approach to achieve this goal. However, distribution variations among cameras inevitably introduce noise in the generated pseudo-labels
-
Adaptive weighted dictionary representation using anchor graph for subspace clustering Pattern Recogn. (IF 8.0) Pub Date : 2024-02-23 Wenyi Feng, Zhe Wang, Ting Xiao, Mengping Yang
Samples are commonly represented as sparse vectors in many dictionary representation algorithms. However, this method may result in loss of discriminatory information. Moreover, a redundant dictionary can increase the computational complexity of the algorithm. To tackle these challenges, we propose a novel method named Adaptive Weighted Dictionary Representation using Anchor Graph for Subspace Clustering
-
Coordinating explicit and implicit knowledge for knowledge-based VQA Pattern Recogn. (IF 8.0) Pub Date : 2024-02-22 Qunbo Wang, Jing Liu, Wenjun Wu
Pre-trained models often generate plausible looking statements that are factually incorrect because of the inaccurate implicit knowledge contained in the model’s parameters. Related methods retrieve explicit knowledge from the external knowledge source to help improve the prediction performance and reliability. However, these methods often use weak training signals for the retriever, and require the
-
Relation fusion propagation network for transductive few-shot learning Pattern Recogn. (IF 8.0) Pub Date : 2024-02-22 Yixiang Huang, Hongyu Hao, Weichao Ge, Yang Cao, Ming Wu, Chuang Zhang, Jun Guo
Previous graph-based meta-learning approaches have explored pairwise feature similarity to learn instance-level relations of samples, however, the gap between the sample relations in feature and label spaces is often ignored. It is empirically observed that instances with different labels may display considerable similarity in visual characteristics, making it challenging to distinguish between them
-
Motion-guided and occlusion-aware multi-object tracking with hierarchical matching Pattern Recogn. (IF 8.0) Pub Date : 2024-02-22 Yujin Zheng, Hang Qi, Lei Li, Shan Li, Yan Huang, Chu He, Dingwen Wang
In the field of multi-target tracking, the widely embraced tracking-by-detection paradigm has rapidly progressed with the refinement of detectors and matching techniques. However, the paradigm of joint detection and tracking is relatively limited, and it is difficult to model complex scenes, such as the complexities introduced by camera motion and occlusion. In this work, a hierarchical joint detection
-
Semi-supervised imbalanced multi-label classification with label propagation Pattern Recogn. (IF 8.0) Pub Date : 2024-02-21 Guodong Du, Jia Zhang, Ning Zhang, Hanrui Wu, Peiliang Wu, Shaozi Li
Multi-label learning tasks usually encounter the problem of the class-imbalance, where samples and their corresponding labels are non-uniformly distributed over multi-label data space. It has attracted increasing attention during the past decade, however, there is a lack of methods capable of handling the imbalanced problem in a semi-supervised setting. This study proposes a label propagation technique
-
Multi-granularity Cross Transformer Network for person re-identification Pattern Recogn. (IF 8.0) Pub Date : 2024-02-21 Yanping Li, Duoqian Miao, Hongyun Zhang, Jie Zhou, Cairong Zhao
Person re-identification (Re-ID) aims to retrieve the same person in the gallery. Transformers have been introduced to the Re-ID task due to their excellent ability to model long-range dependency. However, due to the properties of the global attention mechanism, they are less effective in capturing the discriminative local semantics of pedestrians compared to convolutional operations. To address this
-
Enhancing identification for person search with multi-scale multi-grained representation learning Pattern Recogn. (IF 8.0) Pub Date : 2024-02-21 Zhixiong Han, Bingpeng Ma
Person Search aims to simultaneously address Person Detection and Person Re-ID. There are various challenges in person search such as significant scale variations, occlusions, and partial instances. In this paper, we propose a Multi-Scale Multi-Grained (MSMG) sequential network for end-to-end person search, intended to alleviate these issues. To generate re-id representations robust to scale changes
-
Revisiting single-step adversarial training for robustness and generalization Pattern Recogn. (IF 8.0) Pub Date : 2024-02-21 Zhuorong Li, Daiwei Yu, Minghui Wu, Sixian Chan, Hongchuan Yu, Zhike Han
Recently, single-step adversarial training has received high attention because it shows robustness and efficiency. However, a phenomenon referred to as “catastrophic overfitting” has been observed, which is prevalent in single-step defenses and may frustrate attempts to use FGSM adversarial training. To address this issue, we propose a novel method, (). SEAT mitigates catastrophic overfitting by harnessing
-
Robust multi-view learning via M-estimator joint sparse representation Pattern Recogn. (IF 8.0) Pub Date : 2024-02-21 Yutao Hu, Yulong Wang, Han Li, Hong Chen
Recently, multi-view learning has achieved extraordinary success in many research areas such as pattern recognition and data mining. Most existing multi-view methods mainly focus on exploring the correlation information between different views and their performance may severely degrade in the presence of heavy noises and outliers. In this paper, we put forward a robust multi-view joint sparse representation
-
Efficient image analysis with triple attention vision transformer Pattern Recogn. (IF 8.0) Pub Date : 2024-02-21 Gehui Li, Tongtong Zhao
This paper introduces TrpViT, a novel triple attention vision transformer that efficiently captures both local and global features. The proposed architecture tackles global information acquisition by employing three complementary attention mechanisms in a unique attention block: Window, Dilated, and Channel attention. This attention block extracts spatially local features while expanding the receptive
-
Adapt only once: Fast unsupervised person re-identification via relevance-aware guidance Pattern Recogn. (IF 8.0) Pub Date : 2024-02-21 Jinjia Peng, Jiazuo Yu, Chengjun Wang, Huibing Wang, Xianping Fu
Unsupervised domain adaptive person re-identification (UDA person reID) defines a task where labels in target domains are totally unknown while source domains are fully labeled. Assigning reliable labels quickly is a critical issue for UDA person reID that could be applied in the real-world scenarios. Recent studies focus on obtaining pseudo labels by clustering algorithms and then training the reID
-
FApSH: An effective and robust local feature descriptor for 3D registration and object recognition Pattern Recogn. (IF 8.0) Pub Date : 2024-02-20 Bao Zhao, Zihan Wang, Xiaobo Chen, Xianyong Fang, Zhaohong Jia
-
Prior based Pyramid Residual Clique Network for human body image super-resolution Pattern Recogn. (IF 8.0) Pub Date : 2024-02-17 Simiao Wang, Yu Sang, Yunan Liu, Chunpeng Wang, Mingyu Lu, Jinguang Sun
Recent research in the analysis of human images, such as human parsing and pose estimation, usually requires input images to have a sufficiently high resolution. However, small images of people are commonly encountered in our daily lives, particularly in surveillance applications. This paper aims to ultra-resolve a tiny person image to its high-resolution counterpart by learning effective feature representations
-
Separate first, then segment: An integrity segmentation network for salient object detection Pattern Recogn. (IF 8.0) Pub Date : 2024-02-17 Ge Zhu, Jinbao Li, Yahong Guo
Current methods aggregate multi-level features or introduce auxiliary information to get more refined saliency maps. However, little attention is paid to how to obtain complete salient objects in cluttered background. To address this problem, we propose an integrity segmentation network (ISNet) with a novel detection paradigm that first separates the targets completely and then segment them finely
-
Discovering causally invariant features for out-of-distribution generalization Pattern Recogn. (IF 8.0) Pub Date : 2024-02-16 Yujie Wang, Kui Yu, Guodu Xiang, Fuyuan Cao, Jiye Liang
Out-of-distribution (OOD) generalization aims to generalize a model trained on source domains to unseen target domains. Recently, causality-based generalization methods have focused on learning invariant causal relationships around the label variable, as causal mechanisms are robust across different domains. However, these methods would yield an inaccurate causal variable set due to the lack of heterogeneous
-
Fast and explainable clustering based on sorting Pattern Recogn. (IF 8.0) Pub Date : 2024-02-16 Xinye Chen, Stefan Güttel
We introduce a fast and explainable clustering method called CLASSIX. It consists of two phases, namely a greedy aggregation phase of the sorted data into groups of nearby data points, followed by the merging of groups into clusters. The algorithm is controlled by two scalar parameters, namely a distance parameter for the aggregation and another parameter controlling the minimal cluster size. Extensive
-
Integrating foreground–background feature distillation and contrastive feature learning for ultra-fine-grained visual classification Pattern Recogn. (IF 8.0) Pub Date : 2024-02-15 Qiupu Chen, Lin Jiao, Fenmei Wang, Jianming Du, Haiyun Liu, Xue Wang, Rujing Wang
In pattern recognition, ultra-fine-grained visual classification (ultra-FGVC) has emerged as a paramount challenge, focusing on sub-category distinction within fine-grained objects. The near-indistinguishable similarities among such objects, combined with the dearth of sample data, intensify this challenge. In response, our FDCL-DA method is introduced, which integrates Foreground–background feature
-
A patch distribution-based active learning method for multiple instance Alzheimer's disease diagnosis Pattern Recogn. (IF 8.0) Pub Date : 2024-02-14 Tianxiang Wang, Qun Dai
Medical data, particularly the complex brain imaging structures, acquisition presents significant difficulties and high diagnostic expenses, resulting in a scarcity of the trainable samples in the real-world scenarios. To overcome this limitation, we present an active learning-based sampling strategy that selects the most informative samples from the unlabeled candidate sample pool for expert annotation