Cross-modal retrieval for rice leaf diseases is crucial for prevention, providing agricultural experts with data-driven decision support to address disease threats and safeguard rice production. To overcome the limitations of current crop leaf disease retrieval frameworks, we focused on four common rice leaf diseases and established the first cross-modal rice leaf disease retrieval dataset (CRLDRD). We introduced cross-modal retrieval to the domain of rice leaf disease retrieval and introduced FHTW-Net, a framework for rice leaf disease image–text retrieval. To address the challenge of matching diverse image categories with complex text descriptions during the retrieval process, we initially employed ViT and BERT to extract fine-grained image and text feature sequences enriched with contextual information. Subsequently, two-way mixed self-attention (TMS) was introduced to enhance both image and text feature sequences, with the aim of uncovering important semantic information in both modalities. Then, we developed false-negative elimination–hard negative mining (FNE-HNM) strategy to facilitate in-depth exploration of semantic connections between different modalities. This strategy aids in selecting challenging negative samples for elimination to constrain the model within the triplet loss function. Finally, we introduced warm-up bat algorithm (WBA) for learning rate optimization, which improves the model’s convergence speed and accuracy. Experimental results demonstrated that FHTW-Net outperforms state-of-the-art models. In image-to-text retrieval, it achieved R@1, R@5, and R@10 accuracies of 83.5%, 92%, and 94%, respectively, while in text-to-image retrieval, it achieved accuracies of 82.5%, 98%, and 98.5%, respectively. FHTW-Net offers advanced technical support and algorithmic guidance for cross-modal retrieval of rice leaf diseases.
Separating wood and leaf components in tree point clouds is one of the key tasks for achieving automated forest inventory and management. To obtain accurate wood‒leaf separation results, traditional methods typically rely on large amounts of annotated point cloud data to train supervised semantic segmentation networks. However, point wise annotation is not only extremely labor-intensive but also time-consuming and costly, which greatly limits the widespread application and adoption of supervised learning methods in wood‒leaf separation tasks. To eliminate the dependence on annotated point clouds, this study explores the feasibility of wood‒leaf separation under completely unsupervised conditions. To this end, we propose an unsupervised semantic segmentation network that is capable of directly extracting wood and leaf components in 3D point clouds. The network adopts a sparse convolutional neural network as the backbone and incorporates two custom-designed modules: the dual point attention (DPA) module and the point cloud feature convolutional integrator (PFCI) module, for enhanced feature fusion and extraction. Semantic classification is then achieved by generating pseudolabels via super point clustering. Based on large-scale public datasets containing coniferous and broadleaf forests, in addition to our self-constructed dataset, our proposed network achieved an overall accuracy (oAcc) of 67.583%, a mean classification accuracy (mAcc) of 50.249%, and a mean intersection over union (mIoU) of 38.512%, and in wood and leaf separation at the tree level, it attained an oAcc of 80.856%, a mAcc of 64.013%, and a mIoU of 49.695%. Across both the forest and tree scenarios, our network outperforms the current state-of-the-art methods, namely, GrowSP and PointDC. Ablation experiments further confirm that each of the proposed modules contributes significantly to improving the segmentation accuracy, and in addition, our segmentation network demonstrates strong robustness even under high occlusion rates and exhibits excellent generalization capability.
Masson pine (Pinus massoniana) is a core timber species in the subtropical regions of Southern China, and the precise monitoring of its growth status and phenotypic characteristics is crucial for forest resource management. To address the segmentation challenges caused by intertwined wood-leaf structures and severe occlusion, this study proposes PineSegNet, an end-to-end deep learning framework for fine-grained semantic segmentation of Masson pine point clouds. The framework adopts an encoder–decoder architecture. In the encoding stage, a Hierarchical Local–Global Aggregation (HLGA) module is introduced to capture multi-scale features through progressive downsampling. This design suppresses noise and enhances high-frequency geometric details of branches. In the decoding stage, a Boundary Refinement Unit (BRU) is designed to effectively curb feature diffusion during the interpolation process, significantly enhancing the clarity of category boundaries. Furthermore, this study develops a composite loss function with a dual-supervisory mechanism, namely the CE-Dice Composite Loss (CDC-Loss), to tackle semantic confusion caused by inter-class geometric similarity and the challenges of extreme sample distribution imbalance. Experimental results demonstrate that on both the self-collected dataset (GAOFENG) and the public dataset (FOR-instance), PineSegNet exhibits exceptional robustness and generalization capability, outperforming all evaluated semantic segmentation baselines under the unified experimental setting. This study provides a reliable technical solution for precision forest resource inventory and tree structural analysis within the framework of smart forestry.