Amid growing demands for data privacy and advances in computational infrastructure, federated learning (FL) has emerged as a prominent distributed learning paradigm. Nevertheless, differences in data distribution (such as covariate and semantic shifts) severely affect its reliability in real-world deployments. To address this issue, we propose FedSDWC, a causal inference method that integrates both invariant and variant features. FedSDWC infers causal semantic representations by modeling the weak causal influence between invariant and variant features, effectively overcoming the limitations of existing invariant learning methods in accurately capturing invariant features and directly constructing causal representations. This approach significantly enhances FL's ability to generalize and detect OOD data. Theoretically, we derive FedSDWC's generalization error bound under specific conditions and, for the first time, establish its relationship with client prior distributions. Moreover, extensive experiments conducted on multiple benchmark datasets validate the superior performance of FedSDWC in handling covariate and semantic shifts. For example, FedSDWC outperforms FedICON, the next best baseline, by an average of 3.04% on CIFAR-10 and 8.11% on CIFAR-100.

Tubular structure segmentation (TSS) is important for various applications, such as hemodynamic analysis and route navigation. Despite significant progress in TSS, domain shifts remain a major challenge, leading to performance degradation in unseen target domains. Unlike other segmentation tasks, TSS is more sensitive to domain shifts, as changes in topological structures can compromise segmentation integrity, and variations in local features distinguishing foreground from background (e.g., texture and contrast) may further disrupt topological continuity. To address these challenges, we propose Topology-enhanced Test-Time Adaptation (TopoTTA), the first test-time adaptation framework designed specifically for TSS. TopoTTA consists of two stages: Stage 1 adapts models to cross-domain topological discrepancies using the proposed Topological Meta Difference Convolutions (TopoMDCs), which enhance topological representation without altering pre-trained parameters; Stage 2 improves topological continuity by a novel Topology Hard sample Generation (TopoHG) strategy and prediction alignment on hard samples with pseudo-labels in the generated pseudo-break regions. Extensive experiments across four scenarios and ten datasets demonstrate TopoTTA's effectiveness in handling topological distribution shifts, achieving an average improvement of 31.81% in clDice. TopoTTA also serves as a plug-and-play TTA solution for CNN-based TSS models.

The Internet of Things encompasses a variety of components, including sensors and controllers, which generate vast amounts of multivariate time series data. Anomaly detection within this data can reveal patterns of behavior that deviate from normal operating states, providing timely alerts to mitigate potential serious issues or losses. The prevailing methodologies for multivariate time series anomaly detection are based on data reconstruction. However, these methodologies face challenges related to insufficient feature extraction and fusion, as well as instability in the reconstruction effectiveness of a single model. In this article, we propose RGAnomaly, a novel data reconstruction-based generative adversarial network model. This model leverages transformers and cross-attention mechanisms to extract and fuse the temporal and metric features of multivariate time series. RGAnomaly constructs a joint generator comprising an autoencoder and a variational autoencoder, which forms the adversarial structure with a discriminator. The anomaly score is derived from the combined data reconstruction loss and discrimination loss, providing a more comprehensive evaluation for anomaly detection. Comparative experiments and ablation studies on four public multivariate time series datasets demonstrate that RGAnomaly delivers superior performance in anomaly detection, effectively identifying anomalies in time series data within IoT environments. • Data reconstruction-based generative adversarial network that effectively detects anomalies. • Extraction and fusion of temporal and metric improve the ability of anomaly discrimination. • Integration of multiple data reconstruction models ensures the stability of data reconstruction.

Cracks are common on pavements. Accurate crack detection plays a vital role in pavement maintenance. However, cracks have rich and varied morphological features and fine edges, making this task challenging. Additionally, noise factors such as stains, scratches, and complex textures in the pavement background can easily be confused with cracks, increasing the risk of false prediction in the segmentation process. Therefore, we propose Background Morphology Learning (BML) to reconstruct morphological features of the pavement background noise, extract background morphological dissimilarity maps to suppress interference and reduce false alarms. In addition, we propose Crack Morphology-aware Attention (CMA), which adaptively learns the morphological shape of cracks and dynamically adjusts the shape of the attention receptive field to the topological features of the cracks. This significantly improves the completeness of segmentation. Our method mitigates the problems of false alarms and incomplete segmentation results in the crack segmentation task. Therefore, we propose a Morphology-Aware Transformer (MorFormer) that achieves state-of-the-art results on five public datasets. Moreover, we propose a large-scale cross-domain benchmark for crack segmentation, where MorFormer exhibits excellent domain generalization.

Visible-Infrared Person Re-Identification (VI-ReID) plays a crucial role in round-the-clock security surveillance systems, aiming to detect consistent identity recognition across transitions from day to night. A significant challenge in this field is the variation in the appearance of the same identity across visible and infrared modalities, which often leads to coupled noisy labels, referring to both Noisy Annotation (NA) and Noisy Correspondence (NC). Therefore, learning noisy-tolerant and discriminative representations is the primary objective in VI-ReID. However, existing research typically faces two principal limitations: (1) Learning strategies for noisy labeled scenarios usually rely on analyzing the distribution of loss response while ignoring the rich semantic information from neighboring samples. (2) When dealing with identified noisy samples, most previous approaches usually employ filtering strategies to mitigate the impact of noisy samples but fail to consider the valuable information in the noisy samples. To address these challenges, we propose a Propagation based Recycling Contrastive Learning (PRCL) approach. This method utilizes a label propagation strategy to distinguish clean annotations to learn identity-wise semantic information and recycles filtered noisy samples to capture the geometric-wise representation. Thus, even in the presence of noisy labels, the method can help learn robust representations across visible and infrared modalities. Specifically, we design a Noisy-aware Heterogeneous Graph Propagation module, which identifies noisy samples by aggregating the effects of neighboring labels using a graph propagation strategy. In addition, we develop a Cross Modality Recycling Debiased Contrastive Learning algorithm, which leverages the identity-wise information from clean samples and geometry-wise information from noisy samples. This approach utilizes identity-wise and geometric-wise information to mitigate the effect of noisy labels and retain as much valuable information as possible. Extensive experiments on two VI-ReID benchmark datasets demonstrate that our proposed method achieves highly competitive performance.

Face Anti-Spoofing (FAS) is crucial for securing face recognition systems against presentation attacks. With ad-vancements in sensor manufacture and multi-modal learning techniques, many multi-modal FAS approaches have emerged. However, they face challenges in generalizing to unseen attacks and deployment conditions. These chal-lenges arise from (1) modality unreliability, where some modality sensors like depth and infrared undergo signifi-cant domain shifts in varying environments, leading to the spread of unreliable information during cross-modal feature fusion, and (2) modality imbalance, where training overly relies on a dominant modality hinders the conver-gence of others, reducing effectiveness against attack types that are indistinguishable by sorely using the dominant modality. To address modality unreliability, we propose the Uncertainty-Guided Cross-Adapter (U-Adapter) to recognize unreliably detected regions within each modality and suppress the impact of unreliable regions on other modal-ities. For modality imbalance, we propose a Rebalanced Modality Gradient Modulation (ReGrad) strategy to rebal-ance the convergence speed of all modalities by adaptively adjusting their gradients. Besides, we provide the first large-scale benchmark for evaluating multi-modal FAS per-formance under domain generalization scenarios. Exten-sive experiments demonstrate that our method outperforms state-of-the-art methods. Source codes and protocols are released on https://github.com/OMGGGGG/mmdg.

The person re-identification task aims to retrieve the same identity under different cameras. The main difficulties of the task lie in the collection of a large amount of annotated data and the diversity of pedestrians. Therefore, how to learn a robust and discriminative representation feature with unlabeled data is the key to this task. The pseudo label based methods have shown significant effectiveness in the field by generating pseudo labels from unlabeled data instead of ground-truth labels. However, existing researches typically suffer two limitations: (1) The extracted features are insufficient to reflect the subtle local semantics; (2) The pseudo labels generated by clustering methods cannot avoid introducing noise, which will seriously affect the performance of the discriminative feature. In this paper, to address the above problems, we propose a Distribution-Guided Hierarchical Calibration Contrastive Network (DHCCN) to better exploit local clues and hierarchical representation, which can consider cross-granularity consistency and reduce the noise of pseudo labels by the calibrated feature distribution. A Hierarchical Feature Extractor is employed to capture the multi-granularity response of each image, and fuse both global salience and local subtle texture information of a pedestrian to generate the hierarchical feature. In addition, to reduce the error of the pseudo labels, we introduce a Feature Distribution Corrector to calibrate noisy features of low-confidence samples evaluated by a Gaussian Mixture Model. At last, we integrate cross-granularity consistency constraint by the difference between the global and local feature, which can help generate more accurate feature embedding and improve robustness of the model. Therefore, we can receive a performance that is close to the supervised person re-identification task by narrowing the gap between the pseudo and ground-truth label. Experiments on four standard benchmarks demonstrate the effectiveness of our method against the state-of-the-art unsupervised re-identification methods. The code is available at https://github.com/Li-Yongxi/2023-DHCCN.

Many real-world Internet of Things (IoT) systems contain various sensor devices. Operating the devices generates a large amount of multivariate time series data, which reflects the changing trends of the devices and the physical environment and provides data services for upstream applications. Given that the quality of IoT services usually depends on the accuracy and integrity of the data, we must guarantee the data’s accuracy. The massive sensor data can be continuously monitored to infer normal and abnormal behaviors through anomaly detection. Therefore, to ensure the stability of IoT infrastructure operation, anomaly detection of sensor data has high research value. In this paper, we propose a new multivariate time series anomaly detection structure that can effectively detect anomalies through an adversarial transformer structure. Additionally, the fused anomaly probability strategy can increase the discrimination between normal and abnormal; the reconstruction error of the first stage as the prior knowledge of the second stage can better detect anomalies. The evaluation experiments are conducted on four public datasets and achieve an average anomaly detection F1-Score higher than 0.89, which validates the effectiveness of our proposed method.

One-class classification (OCC) is a classical problem in computer vision that can be described as the task of classifying outlier class samples (OC samples) from the OCC model trained on inlier class samples (IC samples) when datasets are highly biased toward one class due to the insufficient sample size of the other class. Currently, the adversarial learning OCC (ALOCC) method has been proven to significantly improve OCC performance. However, its drawbacks include instability issues and non-evident reconstruction between the IC and OC samples. Therefore, we propose multihead enhanced self-attention in the ALOCC network, thereby increasing the difference between the IC and OC samples and significantly increasing OCC accuracy compared with ALOCC accuracy. For training, we propose a new loss, called adversarial-balance loss, that effectively solves the training instability problem, further increasing OCC accuracy. The experiments show the effectiveness of the proposed method compared with state-of-art methods.

Property crime like residential burglary is a frequently occurred offence in Beijing. For crime reduction, it is important to know if there are hotspots exist and if it does, how many of them are maintained. In this study, spatial and temporal pattern of residential burglary by Policing command unit of Chaoyang district of Beijing is investigated. The method of ESDA (Exploration of Spatial Data Analysis) is proposed for identifying crime hotspots and test their significance. The results demonstrate that identified significant crime hotspots varied by time of day and day of week. Specifically, the burglary was observed to be clustered in center and south of Chaoyang district but none in northern. While by day of week, the patterns of burglary distribution changed and outliers appeared on Tuesday, Wednesday, Saturday and Sunday. By time of day, the burglary outlier appeared in the period between 18:00 PM and 22:00 PM.

The optical flow estimation is still an open question nowadays. One of the bottlenecks of it is the interpolation speed. In this paper, a saliency guide fast interpolation method is proposed which is more than about 2 times faster than the traditional one. The method runs on CPU without any supervision or semantic segmentation information. To make it faster, a fast saliency detection method is introduced to separate the image into two parts. The non-saliency superpixels are interpolated faster with random search only. The salient superpixels are interpolated by propagation and random search. To keep it accurate, the relative initial movement is used to guide the search area when computing the affine model. A soft affine model evaluation is introduced to make the optical flow result more robust. Extensive experiments on challenging datasets MPI-Sintel and KITTI-15 show that our method is efficient and effective.

We present a novel band weighting strategy that exploits multiple binary support vector machines (SVMs) to maximize interclass spectral distances for multiclass hyperspectral remote image classification. Specifically, we commence by training binary SVMs based on the original training samples. We then balance the bands of training samples by maximizing the modified classification scores for SVMs. This balance scheme enlarges the distances between individual training samples and the SVM hyperplane. For each class, we reformulate the binary SVM objective function based on the balanced training samples, resulting in a weighting vector that associates a weight to each spectral band for the class. For a testing sample, we weight it and then classify it by using the binary SVM, both with respect to every individual class. The classification result is obtained from the classifier with the greatest score. Experiments on two benchmark data sets show the effectiveness of the proposed strategy.

MapReduce is a distributed computing programming framework which provides an effective solution to the data processing challenge. As an open-source implementation of MapReduce, Hadoop has been widely used in practice. The performance of Hadoop MapReduce heavily depends on its configuration settings, so tuning these configuration parameters could be an effective way to improve its performance. However, picking out the optimal configuration settings is not easy for the time consuming nature of MapReduce together with the high dimensional and nonlinear features of its configuration optimization. In this paper, we introduce Predator, an experience guided configuration optimizer, which does not treat the optimization problem as a pure black-box problem but utilizes useful experience learnt from Hadoop MapReduce configuration practice to assist the optimizing process. The optimizer uses job execution time estimated by a practical MapReduce cost model as the objective function, and classifies Hadoop MapReduce parameters into different groups by their different tunable levels to shrink search space. Furthermore, the optimization algorithm of the optimizer uses the idea of subspace division to prevent local optimum problem, and it could also reduce the searching time by cutting down the cost in visiting unpromising points in search space. Experiments on Hadoop clusters demonstrate the effectiveness and efficiency of the optimizer.