Segmentation of cell nuclei from three-dimensional (3D) volumetric fluorescence microscopy images is crucial for biological and clinical analyses. In recent years, convolutional neural networks have become the reliable 3D medical image segmentation standard. However, convolutional layers are limited by their finite receptive fields and weight-sharing mechanisms. Consequently, they struggle to effectively model long-range dependencies and spatial correlations, which may lead to inadequate nuclei segmentation. Moreover, the diversity in nuclear appearance and density poses additional challenges. This work proposes a lightweight multi-layer deep aggregation network, MLDA-Net, incorporating Wide Receptive Field Attention (WRFA). This module effectively simulates the large receptive field generated by self-attention in the Swin Transformer while requiring fewer model parameters. This design implements an extended global sensory field that enhances the ability to capture a wide range of spatial information. In addition, the multiple cross-attention (MCA) module in MLDA-Net enhances the output features of different resolutions from the encoder while maintaining global effectiveness. The Multi-Path Aggregation Feature Pyramid Network (MAFPN) receives multi-scale outputs from the MCA module, generating a robust hierarchical feature pyramid for the final prediction. MLDA-Net outperforms state-of-the-art networks, including 3DU-Net, nnFormer, UNETR, SwinUNETR, and 3DUXNET, on the 3D volumetric datasets NucMM and MitoEM. It achieves average performance improvements of 4% to 7% in F1 score, MIoU, and PQ metrics, thereby establishing new benchmark results.

Automated document processing and circulation systems face critical challenges in achieving reliable retrieval accuracy and robust classification performance, particularly in security-critical organizational environments. Traditional approaches suffer from fundamental limitations, including fixed fusion strategies in hybrid retrieval systems, inability to model inter-document relationships in classification tasks, and lack of confidence estimation for result reliability. This paper introduces AttenFlow, a novel context-aware architecture that revolutionizes document management through two core technical innovations. First, we propose the retriever consensus confidence fusion (RCCF) method, which addresses the limitations of conventional hybrid retrieval approaches by introducing consensus-based fusion strategies that dynamically adapt to retriever agreement levels while providing confidence estimates for results. RCCF measures the consensus between different retrievers through sophisticated ranking and scoring consistency metrics, enabling adaptive weight assignment that amplifies high-consensus results while adopting conservative approaches for uncertain cases. Second, we develop adversarial mutual-attention hybrid-dimensional graph attention network (AM-HDGAT) for text, which transforms document classification by modeling inter-document relationships through graph structures while integrating high-dimensional semantic features and low-dimensional statistical features through mutual-attention mechanisms. The approach incorporates adversarial training to enhance robustness against potential security threats, making it particularly suitable for critical document processing applications. Comprehensive experimental evaluation across multiple benchmark datasets demonstrates the substantial effectiveness of our innovations. RCCF achieves improvements of up to 16.9% in retrieval performance metrics compared to traditional fusion methods while providing reliable confidence estimates. AM-HDGAT for text demonstrates superior classification performance with an average F1-score improvement of 2.23% compared to state-of-the-art methods, maintaining 82.4% performance retention under adversarial attack scenarios. Real-world deployment validation shows a 34.5% reduction in manual processing time and 95.7% user satisfaction scores, establishing AttenFlow as a significant advancement in intelligent document management technology.

Remote sensing change detection is constrained by the high cost of pixel-level annotations, which limits the scalability of deep models for large-area monitoring. Semi-supervised learning (SSL) can leverage unlabeled data, yet existing approaches often rely on generic natural-image augmentations and structure-agnostic representations, resulting in unreliable pseudo-labels under remote-sensing-specific appearance variations such as haze-like veiling, illumination/exposure differences, and sensor noise. In this paper, we propose PhysSANet, a physics-inspired and structure-aware SSL framework for remote sensing change detection. PhysSANet introduces a Physics-Aware Perturbation (PAP) strategy that simulates common acquisition-related variations by sampling parameters from typical ranges and adapting them using image statistics. PAP is metadata-free and does not attempt to recover physical quantities. To further improve boundary-accurate localization, PhysSANet couples PAP with a multi-head structure-aware attention module and a spatial–structural attention enhanced feature pyramid network, which explicitly model geometric cues including boundaries, regional coherence, and multi-scale spatial structure. Moreover, we design a multi-view consistency regularization scheme that integrates teacher–student consistency with appearance-plausibility-aware pseudo-label filtering and structure-aware smoothness, suppressing unreliable pseudo-labels under strong appearance variations. Extensive experiments on three benchmark datasets (LEVIRCD, WHU-CD, and SYSU-CD) demonstrate the effectiveness of PhysSANet across varying supervision levels. With only 5% labeled data, PhysSANet achieves 82.3% IoU on WHU-CD, 81.9% on LEVIR-CD, and 63.6% on SYSU-CD, consistently outperforming strong semi-supervised baselines. These results demonstrate that combining physics-inspired perturbations with structure-aware representation learning improves label efficiency, robustness, and boundary accuracy for semi-supervised remote sensing change detection.