Unmanned Aerial Vehicle (UAV) object detection has witnessed rapid progress in recent years. However, its heavy reliance on labeled data and the assumption of consistent data distributions between training and deployment domains limit its generalization ability, leading to significant performance degradation under domain shifts. To address this challenge arising from substantial discrepancies in feature distributions across UAV images captured under diverse conditions, we propose a novel framework: Adaptive Teacher with Weighted Multi-layer Feature Alignment (WMFA-AT) for cross-domain UAV object detection. WMFA-AT adopts a teacher–student mutual learning paradigm, integrating domain adversarial learning with weighted multi-layer feature alignment and strong-weak data augmentation to effectively mitigate domain discrepancies. Specifically, the student model performs adversarial alignment using multiple domain discriminators applied to different feature layers, where layer-wise transferability is quantitatively estimated and used to adaptively weight the alignment process. This strategy ensures that features from the source and target domains are aligned in a distribution-aware manner. Meanwhile, the teacher model benefits from the student model via mutual learning, incorporating knowledge from both source and target domains while avoiding overfitting to the source. To comprehensively evaluate the proposed approach, we construct four challenging cross-domain UAV object detection benchmarks covering cross-time, cross-camera, cross-view, and cross-weather scenarios. Experimental results demonstrate that WMFA-AT consistently improves detection accuracy across diverse domain shifts, highlighting its robustness, generalization capability, and practical applicability in real-world UAV deployment settings.

Semantic change detection (SCD) effectively captures ground object transition information within change regions, delivering more comprehensive and detailed results than binary change detection (BCD) tasks. The existing multi-task SCD models enable parallel processing of segmentation and BCD of bi-temporal remote sensing images, but they still have shortcomings in feature mining, interaction, and cross-task transfer. To address these limitations, a multi-branch feature interaction network (MBFI-Net) is proposed. MBFI-Net designs parallel encoding branches with attention mechanisms that enhance semantic change perception by jointly modeling global contextual patterns and local details. In addition, MBFI-Net proposes bi-temporal feature interaction (BTFI) and cross-task feature transfer (CTFT) modules to improve feature diversity and representativeness, and combines with prior logical relationship constraints to improve SCD performance. Comparative and ablation studies on the SECOND and Landsat-SCD datasets highlight the superiority and robustness of MBFI-Net, which achieves SeKs of 0.2117 and 0.5543, respectively. Furthermore, MBFI-Net strikes a balance between SCD results and model complexity and has superior detection performance for semantic change categories with a small proportion.

Reliable UAV detection from ground-based cameras remains difficult under changing illumination, complex backgrounds, and residual displacement between visible and infrared sensors. This paper proposes the Bidirectional Feature Alignment and Transfer-Gated Fusion Network (BATF-Net), a dual-stream detector that preserves separate RGB- and infrared-reference coordinate systems. At the C3, C4, and C5 stages of a two-stream YOLOX-s architecture, an offset estimator shared across transfer directions predicts RGB-to-infrared and infrared-to-RGB displacement fields. Bilinear sampling maps each source features into the corresponding reference coordinates, after which a spatial gate derived from local response magnitude and post-alignment cosine similarity controls residual feature transfer. The network is trained end to end with two detection-head losses and requires neither pixel-level registration labels nor an auxiliary geometric objective. Under the stated validation protocol, the RGB-/infrared-reference ${\mathrm{AP}}_{50:95}$ values are 41.9%/56.9% on MM-UAV and 66.3%/60.6% on Anti-UAV. Compared with the RGB–infrared detector preceding MMA-SORT, these values are higher by 0.8/0.4 and 0.4/0.5 percentage points, respectively. BATF-Net requires 50.0 G FLOPs and runs at 167 frames/s, compared with 54.2 G FLOPs and 125 frames/s for the MMA-SORT detector on the reported platform. These results show that bidirectional alignment can improve paired RGB–infrared UAV detection while preserving sensor-specific outputs and real-time throughput on the evaluated platform.