In complex UAV aerial scenes, small object detection tasks face challenges such as extremely low pixel occupancy, strong background interference, and sparse effective features, which are further compounded by environmental factors like low illumination. Consequently, single-modality detection algorithms are prone to severe target feature loss and missed detections. Multi-modal image fusion, which complements the texture details of visible light with the thermal radiation characteristics of infrared, is considered an effective approach to overcome the limitations of single physical imaging. However, conventional fusion mechanisms often suffer from semantic gaps when processing heterogeneous data, easily introducing redundant noise and background false alarms. To further improve the accuracy and robustness of small object detection in UAV aerial scenes, this paper proposes a multi-modal detection network that integrates direction-aware multi-granularity and asymmetric context guidance, termed DMAC-Net. Specifically, a Direction-Aware Granularity Enhancement (DAGE) module is first constructed for unified backbone feature extraction, which captures local directions and contour edges of small objects in UAV aerial images with high sensitivity, and expands the receptive field through a multi-granularity mechanism, effectively suppressing false positives induced by complex backgrounds while enhancing the recall of occluded and weakly featured targets. Additionally, the Asymmetric Context Guided Fusion (ACGF) module builds a spatial mechanism via asymmetric receptive fields and performs semantic soft alignment of cross-modal features with dynamic weight assignment, effectively filtering out artifacts and clutter from cross-modal interaction. Experimental results on multiple aerial datasets, including RGBTDronePerson, AVMS and LLVIP demonstrate that the proposed method outperforms existing mainstream models in terms of overall detection accuracy and missed-detection suppression, while exhibiting strong generalization capability and stability under complex lighting transitions and multi-scale variations in UAV monitoring environments.

Anomaly detection plays a vital role in ensuring product quality and operational safety across various industrial applications, from manufacturing to infrastructure monitoring. However, current methods often struggle with challenges such as limited generalization to complex multimodal anomalies, poor adaptation to domain-specific patterns, and reduced feature discriminability due to domain gaps between pre-trained models and industrial data. To address these issues, we propose AnomNet, a novel deep anomaly detection framework that integrates a lightweight feature adapter module to bridge domain discrepancies and enhance multi-scale feature discriminability from pre-trained backbones. AnomNet is trained using a dual-stage centroid learning strategy: the first stage employs separation and entropy regularization losses to stabilize and optimize the centroid representation of normal samples; the second stage introduces a centroid-based contrastive learning mechanism to refine decision boundaries by adaptively managing inter- and intra-class feature relationships. The experimental results on the MVTec AD dataset demonstrate the superior performance of AnomNet, achieving a 99.5% image-level AUROC and 98.3% pixel-level AUROC, underscoring its effectiveness and robustness for anomaly detection and localization in industrial environments.

In the task of unmanned aerial vehicle UAV-based small object detection within complex aerial scenes, objects are characterized by significant scale variation, extremely low pixel occupancy, and dense distribution. These factors severely limit the feature representation capability and fine-grained information modeling of detectors, leading to frequent false positives and missed detections. Multi-modal image fusion, which leverages complementary information from different sensing modalities, is widely regarded as an effective approach to enhance detection performance. To improve the accuracy and robustness of object detection in aerial scenes, this paper proposes YOLO-CH, a multi-modal fusion detection method based on a dual-stream YOLOv11 architecture. The method develops parallel dual-stream feature extraction branches to encode modality-specific features from visible and infrared images. A Cross-modal Feature Transformer (CFT) module is introduced within the backbone network by step, which employs a self-attention mechanism to model intra-modal and inter-modal global dependencies, achieving deep feature interaction and enhanced representation. Furthermore, to mitigate the issue where multi-scale and small object features are susceptible to background interference, we redesigned and optimized the structure of the neck to form a high-level semantic screening feature pyramid network (High-level Screening Feature Pyramid Network, HSFPN). This module utilizes high-level semantic information in a top-down manner to refine low-level detail representations, thereby improving small object discrimination. Experimental results on the VEDAI and AVMS datasets demonstrate that the proposed method outperforms baseline models in both detection accuracy and robustness, while maintaining strong adaptability and performance across different input scales.