Weakly-supervised point cloud semantic segmentation (WS-PCS) has attracted increasing attention due to the challenge of sparse annotations. A central problem is how to effectively extract informative features from the annotated points, enabling reliable supervision. Although many existing works extend 2D graph convolution to 3D point cloud data, 2D convolution inherently assumes feature localization, which is an assumption that does not hold in point clouds, and lacks consistent semantic offsets. To address this, we propose a novel Bilateral Graph Convolutional (BGC) method, which refines graph edges into two categories: regular edges and offset edges, providing improved guidance for WS-PCS. Firstly, we create the Local Bilateral Relations (LBR) module to learn the relational features of edges in local point cloud graphs, encompassing both regular and offset edges. To the best of our knowledge, we are the first to utilize offset edges to capture irregular semantic offsets in point cloud data. Secondly, we propose the Adaptive Pooling (AP) module, which adaptively pools edge information learned from LBR, enhancing the feature characterization ability by incorporating salient and pervasive features. Finally, we design BGC as BGC-Net and evaluate its performance against recent networks on four datasets, achieving state-of-the-art results.

Palmprint recognition systems experience a significant performance decline in cross-domain scenarios due to domain shift caused by non-identity factors such as capture devices and lighting conditions. To address this issue, this paper introduces a novel deep decoupling framework, the Identity and Style Feature Decoupling Network (ISFDNet), designed to improve the model’s cross-domain generalization. ISFDNet explicitly separates stable identity-related information from variable domain-related style information within palmprint features. The framework incorporates two innovative mechanisms: at the feature level, the Spatially-Aware Separation Module (SASM) adaptively produces complementary spatial attention masks to decouple mixed features into identity and style components; at the image level, the Low-Frequency Disturbance Module (LFDM) creates stylized training samples by perturbing the low-frequency parts of images, encouraging the network to learn identity representations that are insensitive to style variations. Additionally, a carefully designed collaborative supervision strategy combines multiple losses to ensure effective decoupling. Extensive experiments on four publicly available palmprint datasets demonstrate that ISFDNet achieves top performance in both cross-domain and in-domain tests, while significantly enhancing the generalization capabilities of existing networks. The code is released at https://github.com/20201422/ISFDNet.

Current deep learning (DL)-based palmprint verification models rely on centralized training with large datasets, which raises significant privacy concerns due to the sensitive and immutable nature of biometric data. Federated learning (FL), a privacy-preserving distributed learning paradigm, offers a compelling alternative by enabling collaborative model training without the need for data sharing. However, FL-based palmprint verification faces critical challenges, including data heterogeneity from diverse identities and the absence of standardized evaluation benchmarks. This paper addresses these gaps by establishing a comprehensive benchmark for FL-based palmprint verification, which explicitly defines and evaluates two practical scenarios: closed-set and open-set verification. We propose FedPalm, a unified FL framework that balances local adaptability with global generalization. Each client trains a personalized textural expert tailored to local data and collaboratively contributes to a shared global textural expert for extracting generalized features. To further enhance verification performance, we introduce a Textural Expert Interaction Module that dynamically routes textural features among experts to generate refined side textural features. Learnable parameters are employed to model relationships between original and side features, fostering cross-texture-expert interaction and improving feature discrimination. Extensive experiments validate the effectiveness of FedPalm, demonstrating robust performance across both scenarios and providing a promising foundation for advancing FL-based palm-print verification research. The related code has been publicly available at https://github.com/Zi-YuanYang/FedPalm.

Palmprint recognition has emerged as a prominent biometric technology, widely applied in diverse scenarios. Traditional handcrafted methods for palmprint recognition often fall short in representation capability, as they heavily depend on researchers’ prior knowledge. Deep learning (DL) has been introduced to address this limitation, leveraging its remarkable successes across various domains. While existing surveys focus narrowly on specific tasks within palmprint recognition—often grounded in traditional methodologies—there remains a significant gap in comprehensive research exploring DL-based approaches across all facets of palmprint recognition. This article bridges that gap by thoroughly reviewing recent advancements in DL-powered palmprint recognition. This article systematically examines progress across key tasks, including region-of-interest (ROI) segmentation, feature extraction, and security and privacy-oriented challenges. Beyond highlighting these advancements, this article identifies current challenges and uncovers promising opportunities for future research. By consolidating state-of-the-art progress, this review serves as a valuable resource for researchers, enabling them to stay abreast of cutting-edge technologies and drive innovation in palmprint recognition.

Clinical practice reveals that patients frequently suffer from multiple co-occurring diseases, making multi-label classification (MLC) essential for accurate diagnosis. However, current MLC methods face two major challenges: (1) Disease-specific feature entanglement arising from the complex interdisease correlations among comorbidities; and (2) Untrustworthy results due to single-point estimates that lack confidence measurement. In this paper, we attempt to address these challenges at both the model and optimization levels. Specifically, at the model level, we introduce an improved transformer architecture with multi-CLS tokens for feature disentanglement. This architecture effectively captures the relationships among different diseases, while each CLS token integrates class-wise features, further refined by a multimodal method using a vision language model (VLM). At the optimization level, we propose a novel trustworthy MLC loss that aggregates positive/negative evidence for each class, modeling a multi-Beta distribution based on the Theory of Evidence, to generate reliable predictions with uncertainty estimations. Extensive experiments are conducted on publicly available clinical datasets, and the results demonstrate the effectiveness of our proposed method11The code is available at: https://github.com/CYYukio/Trustworthy-Disentangled-Framework..

Reducing radiation doses benefits patients, but the resultant low-dose computed tomography (LDCT) images often suffer from clinically unacceptable noise and artifacts. While deep learning (DL) has shown promise in LDCT reconstruction, it requires large-scale data collection from multiple clients, raising privacy concerns. Federated learning (FL) has been introduced to mitigate these privacy concerns; however, current methods are typically tailored to specific scanning protocols, which limits their generalizability and makes them less effective for unseen protocols. To address these issues, we propose SCANPhysFed, a novel SCanning- and ANatomy-level personalized Physics-Driven Federated learning paradigm for LDCT reconstruction. Since the noise distribution in LDCT data is closely tied to scanning protocols and anatomical structures, we propose a dual-level physics-informed way to address these challenges. Specifically, we incorporate physical and anatomical prompts into our physics-informed hypernetworks to capture scanning- and anatomy-specific information, enabling dual-level physics-driven personalization of imaging features. These prompts are derived from the scanning protocol and the radiology report generated by a medical large language model (MLLM). Subsequently, client-specific decoders project these dual-level personalized imaging features back into the image domain. Besides, to tackle the challenge of unseen data, we introduce a novel protocol vector-quantization strategy (PVQS), which ensures consistent performance across new clients by quantifying unseen scanning codes to the closest match in the scanning codebook. Extensive experimental results demonstrate the superior performance of SCAN-PhysFed on public datasets1.

Mobile and Web-of-Things (WoT) devices at the network edge generate vast amounts of data for machine learning applications, yet privacy concerns hinder centralized model training. Federated Learning (FL) allows clients (devices) to collaboratively train a shared model coordinated by a central server without transferring private data. However, inherent statistical heterogeneity among clients presents challenges, often leading to a dilemma between clients' need for personalized local models and the server's goal of building a generalized global model. Existing FL methods typically prioritize either global generalization or local personalization, resulting in a trade-off between these objectives and limiting the full potential of diverse client data. To address this challenge, we propose a novel framework that enhances both global generalization and local personalization by Rethinking Information Representation in the Federated learning process (FedRIR). Specifically, we introduce Masked Client-Specific Learning (MCSL), which isolates and extracts fine-grained client-specific features tailored to each client's unique data characteristics, thereby enhancing personalization. Meanwhile, the Information Distillation Module (IDM) refines global shared features by filtering out redundant client-specific information, resulting in a purer and more robust global representation that enhances generalization. By integrating refined global features with isolated client-specific features, we construct enriched representations that effectively capture both global patterns and local nuances, thereby improving the performance of downstream tasks on the client. Extensive experiments on diverse datasets demonstrate that FedRIR significantly outperforms state-of-the-art FL methods, achieving up to a 3.93% improvement in accuracy while ensuring robustness and stability in heterogeneous environments. The code is publicly available at https://github.com/Deep-Imaging-Group/FedRIR.

Palmprint recognition is a pivotal biometric modality, renowned for its numerous advantages and applications in the field of biometrics. The Gabor filter is a classic and efficient texture feature extractor abstracted from the nervous system. The existing palmprint texture coding methods only focus on first-order texture features (1TFs), while neglecting discriminative second-order texture features (2TFs). Therefore, this paper proposes multi-order extensions for state-of-the-art (SOTA) palmprint texture coding methods, which makes full usage of 1TFs and 2TFs. A filter is used to extract 1TFs from the palmprint image, and the same filter is applied to extract 2TFs from 1TFs. Here, different methods employ various filters to extract diverse textures. Due to the simultaneous participations of 1TFs and 2TFs in multi-order extension codes, more discriminative features are extracted and fused. The experimental results on three public databases, including contact, noncontact and multispectral acquisition types, show that the accuracies of all the palmprint texture coding methods are remarkably improved by multi-order extension, establishing it as a general framework extendable to other texture-based recognition tasks.

Palmprint recognition has emerged as a prominent biometric authentication method due to its high discriminative power, making it suitable for IoT-based security applications. However, the traditional verification paradigm—requiring identical query and registered palmprints—poses notable limitations. This approach is inconvenient if the registered palmprint is injured. To address these challenges, we draw inspiration from biological insights into the symmetrical development of structures during embryonic growth and propose a novel Cross-Chirality Palmprint Verification (CCPV) framework. CCPV enables authentication using either palm, irrespective of which palm is registered, enhancing flexibility for IoT deployments with diverse user conditions. CCPV incorporates an innovative matching rule to improve robustness and minimize variability. This rule calculates distances by flipping the gallery and query palmprints, averaging the results to produce the final matching score. Considering all potential alignments, this approach reduces variance and boosts reliability, which is critical for ensuring seamless biometric authentication in IoT systems. Complementing this is the cross-chirality (CC) loss, which fosters a robust feature space tailored to cross-chirality matching. The CC loss ensures consistency across four palmprint variants—left, right, flipped left, and flipped right—enabling the model to extract chirality-consistent features. Extensive experiments on public datasets validate our effectiveness under closed-set and open-set scenarios. Furthermore, we demonstrate that CCPV is versatile and can seamlessly integrate with existing palmprint recognition methods to achieve superior performance. This innovation advances state-of-the-art biometric authentication and paves the way for more resilient palmprint recognition systems for IoT applications.

Palmprint recognition has received considerable attention due to its inherent discriminative characteristics. However, conventional methods largely rely on static features extracted from individual images, which limits their representational richness. To address this, we propose a dynamic palmprint verification framework that harnesses generative models to enhance feature representations through dynamic construction and matching strategies. During training, a classifier-guided generative model synthesizes class-aware pairs, and a regularization term is introduced to expand the feature space, while mitigating overfitting. For matching, we reformulate the process as a subspace projection within a locally adaptive feature space, where the original and class-conditioned generated features form the basis of the subspace. This enables the model to capture latent inter-individual relationships and achieve stronger discriminability. Extensive experiments across multiple backbones and public benchmarks validate the effectiveness and robustness of the proposed framework.

Currently global features are usually extracted directly from local patterns in palmprint verification. Furthermore, sequence features for palmprint verification are only used as local features, but the properties of sequence features are not fully utilized. To solve this issue, this paper introduces Sequence Feature Fusion Network (SF2Net) for palmprint verification. SF2Net proposes a new paradigm: using stable and spatially correlated sequence features as an intermediate bridge to generate robust global representations. SF2Net’s core mechanism is to first extract fine-grained local features that are then converted into sequence features by a sequence feature extractor (SFE). Finally, the sequence features are used as a superior input to capture high-quality global features. By fusing multi-order texture-based local features with globally extracted sequence features, SF2Net achieves superior discrimination. To ensure high accuracy even with limited training data, a hybrid loss function is proposed, which integrate a cross-entropy loss and a triplet loss. Triplet loss effectively optimizes feature separation by explicitly considering negative samples. Extensive experiments on multiple publicly available palmprint datasets demonstrate that SF2Net achieves state-of-the-art (SOTA) performance. Remarkably, even with a small training-to-testing ratio (1:9), SF2Net achieves 100% accuracy, surpassing SOTA methods under several benchmark datasets. The code is released at https://github.com/20201422/SF2Net.

In clinical practice, computed tomography (CT) is an important noninvasive inspection technology to provide patients' anatomical information. However, its potential radiation risk is an unavoidable problem that raises people's concerns. Recently, deep learning (DL)-based methods have achieved promising results in CT reconstruction, but these methods usually require the centralized collection of large amounts of data for training from specific scanning protocols, which leads to serious domain shift and privacy concerns. To relieve these problems, in this article, we propose a hypernetwork-based physics-driven personalized federated learning method (HyperFed) for CT imaging. The basic assumption of the proposed HyperFed is that the optimization problem for each domain can be divided into two subproblems: local data adaption and global CT imaging problems, which are implemented by an institution-specific physics-driven hypernetwork and a global-sharing imaging network, respectively. Learning stable and effective invariant features from different data distributions is the main purpose of global-sharing imaging network. Inspired by the physical process of CT imaging, we carefully design physics-driven hypernetwork for each domain to obtain hyperparameters from specific physical scanning protocol to condition the global-sharing imaging network, so that we can achieve personalized local CT reconstruction. Experiments show that HyperFed achieves competitive performance in comparison with several other state-of-the-art methods. It is believed as a promising direction to improve CT imaging quality and personalize the needs of different institutions or scanners without data sharing. Related codes have been released at https://github.com/Zi-YuanYang/HyperFed.

Palmprint biometrics garner heightened attention in palm-scanning payment and social security due to their distinctive attributes. However, prevailing methodologies singularly prioritize texture orientation, neglecting the significant texture scale dimension. We design an innovative network for concurrently extracting intra-scale and inter-scale features to redress this limitation. This paper proposes a scale-aware competitive network (SAC-Net), which includes the Inner-Scale Competition Module (ISCM) and the Across-Scale Competition Module (ASCM) to capture texture characteristics related to orientation and scale. ISCM efficiently integrates learnable Gabor filters and a self-attention mechanism to extract rich orientation data and discern textures with long-range discriminative properties. Subsequently, ASCM leverages a competitive strategy across various scales to effectively encapsulate the competitive texture scale elements. By synergizing ISCM and ASCM, our method adeptly characterizes palm-print features. Rigorous experimentation across three benchmark datasets unequivocally demonstrates our proposed approach’s exceptional recognition performance and resilience relative to state-of-the-art alternatives.

This paper presents a novel multitask learning framework for palmprint biometrics, which optimizes classification and hashing branches jointly. The classification branch within our framework facilitates the concurrent execution of three distinct tasks: identity recognition and classification of soft biometrics, encompassing gender and chirality. On the other hand, the hashing branch enables the generation of palmprint hash codes, optimizing for minimal storage as templates and efficient matching. The hashing branch derives the complementary information from these tasks by amalgamating knowledge acquired from the classification branch. This approach leads to superior overall performance compared to individual tasks in isolation. To enhance the effectiveness of multitask learning, two additional modules, an attention mechanism module and a customized gate control module, are introduced. These modules are vital in allocating higher weights to crucial channels and facilitating task-specific expert knowledge integration. Furthermore, an automatic weight adjustment module is incorporated to optimize the learning process further. This module fine-tunes the weights assigned to different tasks, improving performance. Integrating the three modules above has shown promising accuracies across various classification tasks and has notably improved authentication accuracy. The extensive experimental results validate the efficacy of our proposed framework.

Existing deep learning (DL)-based magnetic resonance imaging (MRI) retrospective motion correction (MoCo) models are typically task-specific, which makes them challenging to generalize to different scenarios w.r.t motions, modalities, planes, and scanner centers. This limitation occurs since the motions of each patient vary, and collecting diverse paired/unpaired motion data is generally costly and infeasible. To deal with this problem, we propose the Equivariant Imaging Prior (EIP) framework to generalize the MoCo tasks toward various scenarios.In this paper, the traditional MRI MoCo tasks, specifically for the multi-scenarios, can be treated as a mask-varying compressed sensing self-supervised problem for MRI reconstruction with corrupted k-space data.To the best of our knowledge, this framework is the first attempt to handle multiple MRI MoCo scenarios with one single DL model. Specifically, stochastic subsampling and modality augmentation are employed for data preparation. Then, a domain generalization-friendly net is carefully designed and an equivariant imaging task is leveraged to learn the mapping from corrupted data to clean images. The experimental results show that the proposed EIP framework achieves impressive adaptability across generalizable MoCo tasks, including but not limited to multi-motion, multi-modality, multi-center, and multi-plane. Furthermore, our EIP demonstrates similar or superior performance to several state-of-the-art models trained in a supervised manner, extending to even motion estimation on the multi-coil raw data. The code is available:https://github.com/wangzhiwen-scu/EIP4MoCo.

In recent years, palmprints have been extensively utilized for individual verification. The abundance of sensitive information in palmprint data necessitates robust protection to ensure security and privacy without compromising system performance. Existing systems frequently use cancelable transformations to protect palmprint templates. However, if an adversary gains access to the stored database, they could initiate a replay attack before the system detects the breach and can revoke and replace the reference template. To address replay attacks while meeting template protection criteria, we propose a dual-level cancelable palmprint verification framework. In this framework, the reference template is initially transformed using a cancelable competition hashing network with a first-level token, enabling the end-to-end generation of cancelable templates. During enrollment, the system creates a negative database (NDB) using a second-level token for further protection. Due to the unique NDB-to-vector matching characteristic, a replay attack involving the matching between the reference template and a compromised instance in NDB form is infeasible. This approach effectively addresses the replay attack problem at its root. Furthermore, the dual-level protected reference template enjoys heightened security, as reversing the NDB is NP-hard. We also propose a novel NDB-to-vector matching algorithm based on matrix operations to expedite the matching process, addressing the inefficiencies of previous NDB methods reliant on dictionary-based matching rules. Extensive experiments conducted on public palmprint datasets confirm the effectiveness and generality of the proposed framework. Upon acceptance of the paper, the code will be accessible athttps://github.com/Zi-YuanYang/DCPV.

Spectral computed tomography (CT) is an emerging technology, that generates a multienergy attenuation map for the interior of an object and extends the traditional image volume into a 4-D form. Compared with traditional CT based on energy-integrating detectors, spectral CT can make full use of spectral information, resulting in high resolution and providing accurate material quantification. Numerous model-based iterative reconstruction methods have been proposed for spectral CT reconstruction. However, these methods usually suffer from difficulties such as laborious parameter selection and expensive computational costs. In addition, due to the image similarity of different energy bins, spectral CT usually implies a strong low-rank prior, which has been widely adopted in current iterative reconstruction models. Singular value thresholding (SVT) is an effective algorithm to solve the low-rank constrained model. However, the SVT method requires a manual selection of thresholds, which may lead to suboptimal results. To relieve these problems, in this article, we propose a sparse and low-rank unrolling network (SOUL-Net) for spectral CT image reconstruction, that learns the parameters and thresholds in a data-driven manner. Furthermore, a Taylor expansion-based neural network backpropagation method is introduced to improve the numerical stability. The qualitative and quantitative results demonstrate that the proposed method outperforms several representative state-of-the-art algorithms in terms of detail preservation and artifact reduction.

This paper presents a summary of the Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Data (SynFacePAD 2023) held at the 2023 International Joint Conference on Biometrics (IJCB 2023). The competition attracted a total of 8 participating teams with valid submissions from academia and industry. The competition aimed to motivate and attract solutions that target detecting face presentation attacks while considering synthetic-based training data motivated by privacy, legal and ethical concerns associated with personal data. To achieve that, the training data used by the participants was limited to synthetic data provided by the organizers. The submitted solutions presented innovations and novel approaches that led to outperforming the considered baseline in the investigated benchmarks.

In recent years, automatic check-out (ACO) gains increasing interest and has been widely used in daily life. However, current works mainly rely on both counter and product prototype images in the training phase, and it is hard to maintain the performance in an incremental setting. To deal with this problem, we propose a robust prototype-free retrieval method (ROPREM) for ACO, which is a cascaded framework composed of a product detector module and a product retrieval module. We use the product detector module without product class information to locate products. Additionally, we first attempt the check-out process as a retrieval process rather than a classification process. The retrieval result is considered as the product class by comparing the feature similarity between a query image and gallery templates. As a result, our method require much fewer training samples and achieves state-of-the-art performance on the public Retail Product Checkout (RPC) dataset.

U-shaped networks have become prevalent in various medical image tasks such as segmentation, and restoration. However, most existing U-shaped networks rely on centralized learning which raises privacy concerns. To address these issues, federated learning (FL) and split learning (SL) have been proposed. However, achieving a balance between the local computational cost, model privacy, and parallel training remains a challenge. In this articler, we propose a novel hybrid learning paradigm called Dynamic Corrected Split Federated Learning (DC-SFL) for U-shaped medical image networks. To preserve data privacy, including the input, model parameters, label and output simultaneously, we propose to split the network into three parts hosted by different parties. We propose a Dynamic Weight Correction Strategy (DWCS) to stabilize the training process and avoid the model drift problem due to data heterogeneity. To further enhance privacy protection and establish a trustworthy distributed learning paradigm, we propose to introduce additively homomorphic encryption into the aggregation process of client-side model, which helps prevent potential collusion between parties and provides a better privacy guarantee for our proposed method. The proposed DC-SFL is evaluated on various medical image tasks, and the experimental results demonstrate its effectiveness. In comparison with state-of-the-art distributed learning methods, our method achieves competitive performance.

As a relatively new biometric modality, palmprint attracts much attention for its rich intrinsic features and high commercial prospects. Most existing palmprint recognition methods only extract features from the region of interest (ROI) and neglect the features of other regions. Hence, the recognition performance of these methods highly relies on ROI localization, and it requires users' high cooperation. To relieve these problems, we propose a novel end-to-end recognition framework for contactless whole-palm region-based recognition in this paper, dubbed as Channel Groupwise Drop Network (CGDNet). CGDNet consists of a trunk branch and a part exciting branch. The trunk branch extracts the global representations, and the global scale (GS) module is designed to measure the similarity from feature positions to obtain global knowledge. In the part exciting branch, the features are split into two fine-grained parts equally along the horizontal direction. Then, the channel group-wise drop (CGD) module is designed to aggregate the same part features of the object and cooperates with the CGD mask, which randomly drops the same region in the channel group to excite diverse fine-grained features for learning. Finally, fine-grained features and the global features are concatenated as the final feature. The proposed CGDNet achieves competitive performance in two bench-mark datasets compared with the state-of-the-art methods.

Abstract Energy inequality caused by the process of cluster head election has a large influence on energy efficiency and the network lifetime of wireless sensor networks (WSNs). To this end, a novel concept of EI ec is proposed to evaluate the equality degree of energy consumption. Related theorems for establishing the candidate set of cluster heads are proposed, with the aim of promoting energy equality in each cluster. Subsequently, a novel energy‐efficiency‐adaptive cluster formation mechanism based on economic (ECFE) theory is proposed and detailed. Finally, extensive experiments are carried out to assess its energy efficiency and the network performance by comparisons with the existing classic and latest intelligent clustering algorithms. The results indicate that ECFE improves not only the energy efficiency but also the network performance effectively.