Stomata play a crucial role in plant immune responses, with their morphological characteristics closely linked to disease resistance. Accurate detection and analysis of stomatal phenotypic parameters are essential for soybean disease resistance research and variety breeding. However, traditional stoma detection methods are challenged by complex backgrounds and leaf vein structures in soybean images. To address these issues, we proposed a Soybean Stoma-YOLO (You Only Look Once) model (SS-YOLO) by incorporating large separable kernel attention (LSKA) in the Spatial Pyramid Pooling-Fast (SPPF) module of YOLOv8 and Deformable Large Kernel Attention (DLKA) in the Neck part. These architectural modifications enhanced YOLOV8′s ability to extract multi-scale and irregular stomatal features, thus improving detection accuracy. Experimental results showed that SS-YOLO achieved a detection accuracy of 98.7%. SS-YOLO can effectively extract the stomatal features (e.g., length, width, area, and orientation) and calculate related indices (e.g., density, area ratio, variance, and distribution). Across different soybean rust disease stages, the variety Dandou21 (DD21) exhibited less variation in length, width, area, and orientation compared with Fudou9 (FD9) and Huaixian5 (HX5). Furthermore, DD21 demonstrated greater uniformity in stomatal distribution (SEve: 1.02–1.08) and a stable stomatal area ratio (0.06–0.09). The analysis results indicate that DD21 maintained stable stomatal morphology with rust disease resistance. This study demonstrates that SS-YOLO significantly improved stoma detection and provided valuable insights into the relationship between stomatal characteristics and soybean disease resistance, offering a novel approach for breeding and plant disease resistance research.

With the continuous development of artificial intelligence, effectively solving the problem of data islands under the premise of protecting user data privacy has become a top priority. Federal learning is an effective solution to the two significant dilemmas of data islands and data privacy protection. However, there are still some security problems in federal learning. Therefore, this study simulates the data distribution in a hardware-based trusted execution environment in the real world through two processing methods: independent identically distributed and non-independent identically distributed methods. The basic model uses ResNet164 and innovatively introduces a greedy hierarchical training strategy to gradually train and aggregate complex models to ensure that the training of each layer is optimized under the premise of protecting privacy. The experimental results show that under the condition of an IID data distribution, the final accuracy of the greedy hierarchical model reaches 86.72%, which is close to the accuracy of the unpruned model at 89.60%. In contrast, under the non-IID condition, the model’s performance decreases. Overall, the TEE-based hierarchical federated learning method shows reasonable practicability and effectiveness in a resource-constrained environment. Through this study, the advantages of the greedy hierarchical federated learning model with regard to enhancing data privacy protection, optimizing resource utilization, and improving model training efficiency are further verified, providing new ideas and methods for solving the data island and data privacy protection problems.

Partial multi-label learning (PML) assigns each instance a candidate label set that contains all relevant labels but may also include irrelevant noisy ones, making reliable disambiguation essential. Although a small number of verified clean labels is often available in practice, existing PML methods rarely exploit such information to explicitly guide candidate-label correction. Meanwhile, directly applying knowledge distillation (KD) to PML is highly vulnerable to noisy supervision during representation learning, which can aggravate error accumulation under overlapping candidate labels. To address these issues, we propose a meta-guided distillation framework for PML that integrates teacher–student learning with nested meta-optimization. Specifically, the teacher is optimized with large-scale noisy data under the guidance of limited clean labels, so that it can learn calibrated probabilistic label semantics and generate corrected soft targets for student training. To make this meta-correction process scalable, a truncated meta-gradient approximation is further adopted to reduce computational overhead. The resulting corrected teacher outputs are then used to drive robust multi-label distillation for the student. Experiments on multiple benchmark multi-label image datasets demonstrate consistent improvements over seven representative PML methods across standard evaluation metrics. These results show that meta-guided calibration effectively reduces semantic ambiguity and mitigates noise-induced error propagation in partial multi-label learning.