With the wide application of Underwater Wireless Sensor Networks (UWSNs) in various fields, more and more attention has been paid to deploying and adjusting network nodes. A UWSN is composed of nodes with limited mobility. Drift movement leads to the network structure’s destruction, communication performance decline, and node life-shortening. Therefore, a Node Adjustment Scheme based on Motion Prediction (NAS-MP) is proposed, which integrates the layered model of the ocean current’s uneven depth, the layered ocean current prediction model based on convolutional neural network (CNN)–transformer, the node trajectory prediction model, and the periodic depth adjustment model based on the Seagull Optimization Algorithm (SOA), to improve the network coverage and connectivity. Firstly, the error threshold of the current velocity and direction in the layer was introduced to divide the depth levels, and the regional current data model was constructed according to the measured data. Secondly, the CNN–transformer hybrid network was used to predict stratified ocean currents. Then, the prediction data of layered ocean currents was applied to the nodes’ drift model, and the nodes’ motion trajectory prediction was obtained. Finally, based on the trajectory prediction of nodes, the SOA obtained the optimal depth of nodes to optimize the coverage and connectivity of the UWSN. Experimental simulation results show that the performance of the proposed scheme is superior.

Open-vocabulary object detectors enable prompt-driven recognition, yet their zero-shot transfer to unmanned aerial vehicle (UAV) imagery remains fragile under domain shift, where tiny and cluttered targets depend on weak fine-grained cues. We propose AeroPinWorld, a pinwheel-augmented YOLO-World v2 that revisits stride-2 downsampling as a key transfer bottleneck: aggressive resolution reduction can induce aliasing-driven detail loss and sampling-phase sensitivity, which disproportionately harms small-object representations and degrades cross-dataset generalization in aerial scenes. To address this, AeroPinWorld introduces pinwheel-shaped convolution (PConv) as a phase-aware reduction operator. PConv probes complementary offsets via asymmetric padding and directional kernels before feature fusion, strengthening local structure aggregation at downsampling junctions. Importantly, we do not replace all downsampling operations; instead, we selectively substitute PConv at critical pyramid transitions, including the first two backbone reductions (P1/2 and P2/4) and the two bottom-up stride-2 reductions in the head, while keeping later backbone stages unchanged to preserve efficiency. We evaluate under a strict zero-shot cross-dataset protocol by training on COCO2017 for 24 epochs from official pretrained weights and directly testing on two UAV benchmarks, VisDrone2019-DET and UAVDT, without any target-domain fine-tuning, using an offline prompt vocabulary at inference. Experiments demonstrate consistent improvements over the baseline, achieving a +2.3 mAP gain and a +0.9 APS gain on VisDrone, and yielding consistent gains on UAVDT, while maintaining a competitive efficiency profile.

Zero-Shot Learning (ZSL) aims to recognize unseen classes by leveraging semantic knowledge from seen categories. However, inductive ZSL models suffer from domain shift—a visual-semantic misalignment that undermines generalization. To address this, we introduce ZM-VAEGAN, a framework that integrates a Structure-Aligned VAEGAN with Vision Mamba to capture long-range visual dependencies. Our Structural Alignment (SA) mechanism explicitly models inter- and intra-class relationships, reducing confusion among similar categories to enhance visual-semantic consistency. ZM-VAEGAN employs a bidirectional adversarial learning strategy, aligning visual and semantic spaces through forward synthesis and inverse projection. To bridge the cross-modal gap, we introduce Semantic-aware Local Projection (SLP) and Global Representation Learning (GRL) modules to map visual representations into the semantic space at multiple granularities. Extensive experiments on four benchmarks demonstrate that ZM-VAEGAN achieves state-of-the-art performance in both ZSL and generalized ZSL settings, confirming its effectiveness and structural robustness.

Zero-shot learning (ZSL) addresses scarce samples and unseen categories in industrial defect detection. Zero-shot multi-type anomaly segmentation (MTAS) demands both anomaly localization and fine-grained defect classification, yet mainstream methods like MultiADS face an inherent alignment-generalization paradox: they rely on static prompts and one-way alignment, failing to adapt to fine-grained visual variations and limiting accuracy.To tackle this, we propose the Dynamic Anomaly-Aware Segmentation (DAAS) framework for zero-shot industrial defect detection. Its core is a customized training-only Post-VCP module. Based on industrial defect-tailored multi-head cross-attention over local visual features, this module provides strong supervision for text embedding learning, preserves semantic priors via residual connections, and enhances the fine-grained modeling ability of static text embeddings for inference.Extensive transductive experiments on four benchmarks (MVTec-AD, VisA, MPDD, MAD-real) show DAAS achieves substantial gains on MTAS over MultiADS, with competitive results on binary ZSL. These validate our method’s effectiveness, theoretical rationality and robustness in real industrial scenarios.

Open-vocabulary object detection in unmanned aerial vehicle (UAV) imagery remains challenging under zero-shot cross-dataset transfer because tiny and cluttered targets are highly sensitive to early resolution reduction under domain shift. This study aims to improve transferable open-vocabulary UAV detection by revisiting stride-2 downsampling in YOLO-World v2 as a transfer-critical bottleneck. AeroPinWorld is introduced as a pinwheel-augmented YOLO-World v2 that selectively replaces four key stride-2 transitions with pinwheel-shaped convolution (PConv) so as to reduce aliasing, alleviate sampling-phase sensitivity, and preserve fine-grained local structures, while keeping the original detection head unchanged to ensure a fair and efficient comparison. The model is trained on COCO2017 for 24 epochs from official pretrained weights and directly evaluated, without target-domain fine-tuning, on VisDrone2019-DET and UAVDT using fixed offline prompt vocabularies. Compared with YOLO-World v2-S, AeroPinWorld improves zero-shot transfer performance on VisDrone from 0.112 to 0.135 mAP and from 0.054 to 0.063 AP_S, and it also yields consistent gains on UAVDT. Ablation studies show that both early backbone replacements and head bottom–up replacements contribute to the final gains, with their combination achieving the best accuracy–efficiency trade-off. These results indicate that selectively redesigning transfer-critical downsampling operators is an effective and lightweight way to improve zero-shot open-vocabulary UAV detection under aerial domain shift.