Intra-class Similarity Research Articles

Debiased hybrid contrastive learning with hard negative mining for unsupervised person re-identification

The goal of unsupervised person re-identification is to retrieve a specific person across several non-overlapping cameras without the aid of manual labeling information. In recent times, contrastive learning has found extensive application in undertaking the complexities of unsupervised person Re-ID. Nevertheless, prevailing approaches often ignore the bias in negative proxy sampling and the significance of hard negatives in contrastive learning. These limitations have constrained the performance of existing methods. To solve these issues, we introduce a Debiased Hybrid Contrastive Learning with Hard Negative Mining (DHCL-HNM) approach. Particularly, the proposed approach employs an instance-level memory bank to save the class prototypes for all training images. In each training epoch, the memory bank undergoes clustering, dividing the dataset into un-clustered outliers and clustered images with pseudo labels. Then, the debiasing of negative proxies and the hard negative mining are integrated into a hybrid contrastive learning process to enhance the intra-class similarity and the instance discrimination. The debiasing operation is realized during the sampling of negative proxies to reduce the negative effects of false negatives. In the meantime, the hard negative mining can guide the Re-ID model to concentrate on the hard negatives by reweighting negative proxies based on their similarities to the anchor sample. The efficiency of the proposed method in the realm of unsupervised person Re-ID is demonstrated through comprehensive experiment outcomes conducted on several datasets.

Efficient Discrete Clustering With Anchor Graph.

Spectral clustering (SC) has been applied to analyze varieties of data structures over the past few decades owing to its outstanding breakthrough in graph learning. However, the time-consuming eigenvalue decomposition (EVD) and information loss during relaxation and discretization impact the efficiency and accuracy especially for large-scale data. To address above issues, this brief proposes a simple and fast method named efficient discrete clustering with anchor graph (EDCAG) to circumvent postprocessing by binary label optimization. First of all, sparse anchors are adopted to accelerate graph construction and obtain a parameter-free anchor similarity matrix. Subsequently, inspired by intraclass similarity maximization in SC, we design an intraclass similarity maximization model between anchor-sample layer to cope with anchor graph cut problem and exploit more explicit data structures. Meanwhile, a fast coordinate rising (CR) algorithm is employed to alternatively optimize discrete labels of samples and anchors in designed model. Experimental results show excellent rapidity and competitive clustering effect of EDCAG.

Few-Shot Relation Extraction With Dual Graph Neural Network Interaction.

Recent advances in relation extraction with deep neural architectures have achieved excellent performance. However, current models still suffer from two main drawbacks: 1) they require enormous volumes of training data to avoid model overfitting and 2) there is a sharp decrease in performance when the data distribution during training and testing shift from one domain to the other. It is thus vital to reduce the data requirement in training and explicitly model the distribution difference when transferring knowledge from one domain to another. In this work, we concentrate on few-shot relation extraction under domain adaptation settings. Specifically, we propose DUAL GRAPH, a novel graph neural network (GNN) based approach for few-shot relation extraction. DUAL GRAPH leverages an edge-labeling dual graph (i.e., an instance graph and a distribution graph) to explicitly model the intraclass similarity and interclass dissimilarity in each individual graph, as well as the instance-level and distribution-level relations across graphs. A dual graph interaction mechanism is proposed to adequately fuse the information between the two graphs in a cyclic flow manner. We extensively evaluate DUAL GRAPH on FewRel1.0 and FewRel2.0 benchmarks under four few-shot configurations. The experimental results demonstrate that DUAL GRAPH can match or outperform previously published approaches. We also perform experiments to further investigate the parameter settings and architectural choices, and we offer a qualitative analysis.

Innovative multi-stage matching for counting anything

Few-shot counting (FSC) is the task of counting the number of objects in an image that belong to the same category, by using a provided exemplar pattern. By replacing the exemplar, we can effectively count anything, even in cases where we have no prior knowledge of that category’s exemplar. However, due to the variations within the same category and the impact of inter-class similarity, it is challenging to achieve accurate intra-class similarity matching using conventional similarity comparison methods. To tackle these issues, we propose a novel few-shot counting method called Multi-stage Exemplar Attention Match Network (MEAMNet), which increases the accuracy of matching, reduces the impact of noise, and enhances similarity feature matching. Specifically, we propose a multi-stage matching strategy to obtain more stable and effective matching results by acquiring similar feature in different feature spaces. In addition, we propose a novel feature matching module called Exemplar Attention Match (EAM). With this module, the intra-class similarity representation in each stage will be enhanced to achieve a better matching of the key feature. Experimental results indicate that our method not only significantly surpasses the state-of-the-art (SOTA) methods in most evaluation metrics on the FSC-147 dataset but also achieves comprehensive superiority on the CARPK dataset. This highlights the outstanding accuracy and stability of our matching performance, as well as its exceptional transferability. We will release the code at https://github.com/hzg0505/MEAMNet.

IIS-FVIQA: Finger Vein Image Quality Assessment with intra-class and inter-class similarity

In recent years, Finger Vein Image Quality Assessment (FVIQA) has been recognized as an effective solution to the problem of erroneous recognition resulting from low image quality due to false and missing information in finger vein images, and has become an important part of finger vein recognition systems. Compared to traditional FVIQA methods that rely on domain knowledge, newer methods that reject low-quality images have been favored for their independence from human interference. However, these methods only consider intra-class similarity information and ignore valuable information from inter-class distribution, which is also an important factor in evaluating the performance of recognition systems. In this work, we propose a novel FVIQA approach, named IIS-FVIQA, which concurrently takes into account the intra-class similarity density and inter-class similarity distribution distance within recognition systems. Specifically, our method generates quality scores for finger vein images by combining the information entropy of intra-class similarity distribution and Wasserstein distance of inter-class distribution. Then, we train a regression network for quality prediction using training images and corresponding quality scores. When a new image enters the recognition system, the trained regression network directly predicts the quality score of the image, making it easier for the system to select the corresponding operation based on the quality score of the image. Extensive experiments conducted on benchmark datasets demonstrate that the IIS-FVIQA method proposed in this paper consistently achieves top performance across multiple public datasets. After filtering out 10% of low-quality images predicted by the quality regression network, the recognition system’s performance improves by 43.96% (SDUMLA), 32.23% (MMCBNU_6000), and 21.20% (FV-USM), respectively. Furthermore, the method exhibits strong generalizability across different recognition algorithms (e.g., LBP, MC, and Inception V3) and datasets (e.g., SDUMLA, MMCBNU_6000, and FV-USM).

Relevance Pooling Guidance and Class-Balanced Feature Enhancement for Fine-Grained Oriented Object Detection in Remote Sensing Images

Fine-grained object detection in remote sensing images is highly challenging due to class imbalance and high inter-class indistinguishability. The strategies employed by most existing methods to resolve these two challenges are relatively rudimentary, resulting in suboptimal model performance. To address these issues, we propose a fine-grained object-oriented detection method based on relevance pooling guidance and class balance feature enhancement. Firstly, we propose a global attention mechanism that dynamically retains spatial features pertinent to objects through relevance pooling during down-sampling, thereby enabling the model to acquire more discriminative features. Next, a class balance correction module is proposed to alleviate the class imbalance problem. This module employs feature translation and a learnable reinforcement coefficient to highlight the boundaries of tail class features while maintaining their distinctiveness. Furthermore, we present an enhanced contrastive learning strategy. By dynamically adjusting the contribution of inter-class samples and intra-class similarity measures, this strategy not only constrains inter-class feature distances but also facilitates tighter intra-class clustering, making it more suitable for imbalanced datasets. Evaluation on the FAIR1M and MAR20 datasets demonstrates that our method is superior compared to other methods in object detection and achieves 46.44 and 85.05% mean average precision, respectively.

SimMix: Local similarity-aware data augmentation for time series

We find that local similarity is an essential factor for data augmentation in deep learning tasks concerning time series data, the applications of which are prevalent in various domains such as smart healthcare, intelligent transportation, smart finance, etc. With empirical and theoretical analysis, we find deep learning models achieve excellent performance only when the data augmentation method performs with appropriate intensity of local similarity—during the data augmentation process, too large/small intra-class local similarity will decrease the performance of deep learning models. With this discovery, we propose a time series augmentation method based on intra-class Similarity Mixing (SimMix), which accurately controls the intensity by quantifying and adjusting the similarity between augmented samples and original samples. With a PAC (i.e., Probably Approximately Correct) theoretical foundation, we design a cutmix strategy for non-equal length segments to eliminate semantic information loss and noise introduction defects in traditional methods. Through extensive validation on 10 real-world datasets, we demonstrate that the proposed method can outperform the state-of-the-art by a large margin.

CL-TransFER: Collaborative learning based transformer for facial expression recognition with masked reconstruction

Facial expression recognition (FER) has attracted intensive attention due to its critical role in various computer vision tasks. However, existing FER approaches suffer from either noisy annotations or expression ambiguity (high inter-class and low intra-class similarity), limiting the FER performance. To this end, we propose a robust end-to-end collaborative learning based transformer for FER (CL-TransFER) in this paper. Specifically, CL-TransFER co-trains a CNN feature extractor and a transformer feature extractor jointly to extract both rich local semantic features as well as global structural information from facial images. By enforcing the consensus between the predictions of two extractors, the CL-TransFER could suppress the influence of noisy annotations. To further tackle the expression ambiguity problem, we design a simple yet efficient self-supervised masked reconstruction (SSMR) task to pre-train the transformer feature extractor of CL-TransFER. This enhances the model's capability of learning fine-grained discriminative representations. Extensive experiments on three popular benchmarks have demonstrated the effectiveness and superiority of our method.

Probability graph complementation contrastive learning

Graph Neural Network (GNN) has achieved remarkable progress in the field of graph representation learning. The most prominent characteristic, propagating features along the edges, degrades its performance in most heterophilic graphs. Certain researches make attempts to construct KNN graph to improve the graph homophily. However, there is no prior knowledge to choose proper K and they may suffer from the problem of Inconsistent Similarity Distribution (ISD). To accommodate this issue, we propose Probability Graph Complementation Contrastive Learning (PGCCL) which adaptively constructs the complementation graph. We employ Beta Mixture Model (BMM) to distinguish intra-class similarity and inter-class similarity. Based on the posterior probability, we construct Probability Complementation Graphs to form contrastive views. The contrastive learning prompts the model to preserve complementary information for each node from different views. By combining original graph embedding and complementary graph embedding, the final embedding is able to capture rich semantics in the finetuning stage. At last, comprehensive experimental results on 20 datasets including homophilic and heterophilic graphs firmly verify the effectiveness of our algorithm as well as the quality of probability complementation graph compared with other state-of-the-art methods.

Graph Aggregating-Repelling Network: Do Not Trust All Neighbors in Heterophilic Graphs

Graph neural networks (GNNs) have demonstrated exceptional performance in processing various types of graph data, such as citation networks and social networks, etc. Although many of these GNNs prove their superiority in handling homophilic graphs, they often overlook the other kind of widespread heterophilic graphs, in which adjacent nodes tend to have different classes or dissimilar features. Recent methods attempt to address heterophilic graphs from the graph spatial domain, which try to aggregate more similar nodes or prevent dissimilar nodes with negative weights. However, they may neglect valuable heterophilic information or extract heterophilic information ineffectively, which could cause poor performance of downstream tasks on heterophilic graphs, including node classification and graph classification, etc. Hence, a novel framework named GARN is proposed to effectively extract both homophilic and heterophilic information. First, we analyze the shortcomings of most GNNs in tackling heterophilic graphs from the perspective of graph spectral and spatial theory. Then, motivated by these analyses, a Graph Aggregating-Repelling Convolution (GARC) mechanism is designed with the objective of fusing both low-pass and high-pass graph filters. Technically, it learns positive attention weights as a low-pass filter to aggregate similar adjacent nodes, and learns negative attention weights as a high-pass filter to repel dissimilar adjacent nodes. A learnable integration weight is used to adaptively fuse these two filters and balance the proportion of the learned positive and negative weights, which could control our GARC to evolve into different types of graph filters and prevent it from over-relying on high intra-class similarity. Finally, a framework named GARN is established by simply stacking several layers of GARC to evaluate its graph representation learning ability on both the node classification and image-converted graph classification tasks. Extensive experiments conducted on multiple homophilic and heterophilic graphs and complex real-world image-converted graphs indicate the effectiveness of our proposed framework and mechanism over several representative GNN baselines.

Cross-modal learning using privileged information for long-tailed image classification

The prevalence of long-tailed distributions in real-world data often results in classification models favoring the dominant classes, neglecting the less frequent ones. Current approaches address the issues in long-tailed image classification by rebalancing data, optimizing weights, and augmenting information. However, these methods often struggle to balance the performance between dominant and minority classes because of inadequate representation learning of the latter. To address these problems, we introduce descriptional words into images as cross-modal privileged information and propose a cross-modal enhanced method for long-tailed image classification, referred to as CMLTNet. CMLTNet improves the learning of intraclass similarity of tail-class representations by cross-modal alignment and captures the difference between the head and tail classes in semantic space by cross-modal inference. After fusing the above information, CMLTNet achieved an overall performance that was better than those of benchmark long-tailed and cross-modal learning methods on the long-tailed cross-modal datasets, NUS-WIDE and VireoFood-172. The effectiveness of the proposed modules was further studied through ablation experiments. In a case study of feature distribution, the proposed model was better in learning representations of tail classes, and in the experiments on model attention, CMLTNet has the potential to help learn some rare concepts in the tail class through mapping to the semantic space.

ISM: intra-class similarity mixing for time series augmentation

ISM: intra-class similarity mixing for time series augmentation

Stripe-Assisted Global Transformer and Spatial–Temporal Enhancement for Vehicle Re-Identification

As a core technology in intelligent transportation systems, vehicle re-identification has attracted growing attention. Most existing methods use CNNs to extract global and local features from vehicle images and roughly integrate them for identifying vehicles, addressing intra-class similarity and inter-class difference. However, a significant challenge arises from redundant information between global and local features and possible misalignment among local features, resulting in suboptimal efficiency when combined. To further improve vehicle re-identification, we propose a stripe-assisted global transformer (SaGT) method, which leverages a dual-branch network based on transformers to learn a discriminative whole representation for each vehicle image. Specifically, one branch exploits a standard transformer layer to extract a global feature, while the other branch employs a stripe feature module (SFM) to construct stripe-based features. To further facilitate the effective incorporation of local information into the learning process of the global feature, we introduce a novel stripe-assisted global loss (SaGL), which combines ID losses to optimize the model. Considering redundancy, we only use the global feature for inference, as we enhance the whole representation with stripe-specific details. Finally, we introduce a spatial-temporal probability (STPro) to provide a complementary metric for robust vehicle re-identification. Extensive and comprehensive evaluations on two public datasets validate the effectiveness and superiority of our proposed method.

Innovative Cultural Transmission Paths Analysis for Local Opera Based on Data Mining

With the rapid development of society and cultural diversity, local opera, as a representative of traditional art, faces dual challenges of inheritance and innovation. The inheritance of traditional Chinese opera often relies on oral instruction, but in modern society, this method is no longer suitable for the rapidly changing cultural environment. The purpose of this study is to explore in depth the innovative cultural dissemination path of local opera through data mining techniques. This paper uses data mining techniques to explore and analyze the inheritance of innovative culture in local opera, and to study the inheritance paths. This paper proposes a data mining-based method for analyzing and identifying the paths of inheritance of innovative culture in local opera. This paper focuses on two aspects of technology clustering and technology theme association, and the research paths are divided into flexible clustering based on data enhancement and technology evolution path identification based on theme extraction. Firstly, the heritage changes of dating tunes are discussed. Secondly, the unique artistic esthetics of the dating tune is compared with the artistic characteristics of Henan opera and the three-stringed book. Through the research and learning experience of the Dai Yongqu, it is easier to thoroughly understand the artistic essence and cultural connotation of the Dai Yongqu, and that exposure to the Dai Yongqu is a process of touching traditional culture. In the text clustering section, the data co-occurrence frequency matrix is constructed based on the results of multiple clustering, transforming the problem of determining the number of clusters into a co-occurrence frequency problem with semantic information of the text, thus achieving the purpose of flexible clustering on demand. In a comparison with existing methods, the text representation method using data-enhanced coding achieves better semantic coding results. The flexible clustering method can differentiate the data better than the clustering method with a defined number of clusters and obtains clustering results with high intra-class similarity and high inter-class differentiation.

Robust multi-frequency band joint dictionary learning with low-rank representation

Emotional state recognition is an important part of emotional research. Compared to non-physiological signals, the electroencephalogram (EEG) signals can truly and objectively reflect a person’s emotional state. To explore the multi-frequency band emotional information and address the noise problem of EEG signals, this paper proposes a robust multi-frequency band joint dictionary learning with low-rank representation (RMBDLL). Based on the dictionary learning, the technologies of sparse and low-rank representation are jointly integrated to reveal the intrinsic connections and discriminative information of EEG multi-frequency band. RMBDLL consists of robust dictionary learning and intra-class/inter-class local constraint learning. In robust dictionary learning part, RMBDLL separates complex noise in EEG signals and establishes clean sub-dictionaries on each frequency band to improve the robustness of the model. In this case, different frequency data obtains the same encoding coefficients according to the consistency of emotional state recognition. In intra-class/inter-class local constraint learning part, RMBDLL introduces a regularization term composed of intra-class and inter-class local constraints, which are constructed from the local structural information of dictionary atoms, resulting in intra-class similarity and inter-class difference of EEG multi-frequency bands. The effectiveness of RMBDLL is verified on the SEED dataset with different noises. The experimental results show that the RMBDLL algorithm can maintain the discriminative local structure in the training samples and achieve good recognition performance on noisy EEG emotion datasets.

Graph contrastive learning with consistency regularization

Contrastive learning has actively been used for unsupervised graph representation learning owing to its success in computer vision. Most graph contrastive learning methods use instance discrimination. It treats each instance as a distinct class against a query instance as the pretext task. However, such methods inevitably cause a class collision problem because some instances may belong to the same class as the query. Thus, the similarity shared through instances from the same class cannot be reflected in the pre-training stage. To address this problem, we propose graph contrastive learning with consistency regularization (GCCR), which introduces a consistency regularization term to graph contrastive learning. Unlike existing methods, GCCR can obtain a graph representation that reflects intra-class similarity by introducing a consistency regularization term. To verify the effectiveness of the proposed method, we performed extensive experiments and demonstrated that GCCR improved the quality of graph representations for most datasets. Notably, experimental results in various settings show that the proposed method can learn effective graph representations with better robustness against transformations than other state-of-the-art methods.

Mutual learning with reliable pseudo label for semi-supervised medical image segmentation

Semi-supervised learning has garnered significant interest as a method to alleviate the burden of data annotation. Recently, semi-supervised medical image segmentation has garnered significant interest that can alleviate the burden of densely annotated data. Substantial advancements have been achieved by integrating consistency-regularization and pseudo-labeling techniques. The quality of the pseudo-labels is crucial in this regard. Unreliable pseudo-labeling can result in the introduction of noise, leading the model to converge to suboptimal solutions. To address this issue, we propose learning from reliable pseudo-labels. In this paper, we tackle two critical questions in learning from reliable pseudo-labels: which pseudo-labels are reliable and how reliable are they? Specifically, we conduct a comparative analysis of two subnetworks to address both challenges. Initially, we compare the prediction confidence of the two subnetworks. A higher confidence score indicates a more reliable pseudo-label. Subsequently, we utilize intra-class similarity to assess the reliability of the pseudo-labels to address the second challenge. The greater the intra-class similarity of the predicted classes, the more reliable the pseudo-label. The subnetwork selectively incorporates knowledge imparted by the other subnetwork model, contingent on the reliability of the pseudo labels. By reducing the introduction of noise from unreliable pseudo-labels, we are able to improve the performance of segmentation. To demonstrate the superiority of our approach, we conducted an extensive set of experiments on three datasets: Left Atrium, Pancreas-CT and Brats-2019. The experimental results demonstrate that our approach achieves state-of-the-art performance. Code is available at: https://github.com/Jiawei0o0/mutual-learning-with-reliable-pseudo-labels.

Transductive meta-learning with enhanced feature ensemble for few-shot semantic segmentation

This paper addresses few-shot semantic segmentation and proposes a novel transductive end-to-end method that overcomes three key problems affecting performance. First, we present a novel ensemble of visual features learned from pretrained classification and semantic segmentation networks with the same architecture. Our approach leverages the varying discriminative power of these networks, resulting in rich and diverse visual features that are more informative than a pretrained classification backbone that is not optimized for dense pixel-wise classification tasks used in most state-of-the-art methods. Secondly, the pretrained semantic segmentation network serves as a base class extractor, which effectively mitigates false positives that occur during inference time and are caused by base objects other than the object of interest. Thirdly, a two-step segmentation approach using transductive meta-learning is presented to address the episodes with poor similarity between the support and query images. The proposed transductive meta-learning method addresses the prediction by first learning the relationship between labeled and unlabeled data points with matching support foreground to query features (intra-class similarity) and then applying this knowledge to predict on the unlabeled query image (intra-object similarity), which simultaneously learns propagation and false positive suppression. To evaluate our method, we performed experiments on benchmark datasets, and the results demonstrate significant improvement with minimal trainable parameters of 2.98M. Specifically, using Resnet-101, we achieve state-of-the-art performance for both 1-shot and 5-shot Pascal-5i\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$5^{i}$$\\end{document}, as well as for 1-shot and 5-shot COCO-20i\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$20^{i}$$\\end{document}.

GCNFORMER: graph convolutional network and transformer for predicting lncRNA-disease associations.

A growing body of researches indicate that the disrupted expression of long non-coding RNA (lncRNA) is linked to a range of human disorders. Therefore, the effective prediction of lncRNA-disease association (LDA) can not only suggest solutions to diagnose a condition but also save significant time and labor costs. In this work, we proposed a novel LDA predicting algorithm based on graph convolutional network and transformer, named GCNFORMER. Firstly, we integrated the intraclass similarity and interclass connections between miRNAs, lncRNAs and diseases, and built a graph adjacency matrix. Secondly, to completely obtain the features between various nodes, we employed a graph convolutional network for feature extraction. Finally, to obtain the global dependencies between inputs and outputs, we used a transformer encoder with a multiheaded attention mechanism to forecast lncRNA-disease associations. The results of fivefold cross-validation experiment on the public dataset revealed that the AUC and AUPR of GCNFORMER achieved 0.9739 and 0.9812, respectively. We compared GCNFORMER with six advanced LDA prediction models, and the results indicated its superiority over the other six models. Furthermore, GCNFORMER's effectiveness in predicting potential LDAs is underscored by case studies on breast cancer, colon cancer and lung cancer. The combination of graph convolutional network and transformer can effectively improve the performance of LDA prediction model and promote the in-depth development of this research filed.

Semi-Supervised Instance Segmentation in Whole Slide Images via Dense Spatial Variability Enhancing.

Current whole slide image (WSI) segmentation aims at extracting tumor regions from the background. Unlike this, segmenting distinct tumor areas (instances) within a WSI driven by limited annotated data remains under-explored. In this paper, we formally propose semisupervised instance segmentation (Semi-IS) in WSIs. We address a key challenge: learning intra-class similarity and inter-class dissimilarity driven by unlabeled data. Specifically, we generally perceive the patch as composed of tokens (together), not the patch alone. We employ contrastive learning to develop a segmentation framework. In the SemiIS, we find that the boundaries of segmented instances are usually disturbed by noise. We jointly eliminate and preserve noise features to address this problem. We conduct extensive experiments to evaluate the effectiveness and generalizability of Semi-IS, including histopathology and cellular pathology. The results show that in clinical multi instance segmentation tasks, Semi-IS achieves almost fullsupervised state-of-the-art results with only 30% annotated data. Semi-IS can improve segmentation accuracy by about 2% on public cell pathology datasets.