Abstract
Object detection in aerial imagery is a critical task in applications such as UAV reconnaissance. Although existing methods have extensively explored feature interaction between different modalities, they commonly rely on simple fusion strategies for feature aggregation. This introduces two critical flaws: it is prone to cross-modal noise and disrupts the hierarchical structure of the feature pyramid, thereby impairing the fine-grained detection of small objects. To address this challenge, we propose the Pyramidal Adaptive Cross-Gating Network (PACGNet), an architecture designed to perform deep fusion within the backbone. To this end, we design two core components: the Symmetrical Cross-Gating (SCG) module and the Pyramidal Feature-aware Multimodal Gating (PFMG) module. The SCG module employs a bidirectional, symmetrical "horizontal" gating mechanism to selectively absorb complementary information, suppress noise, and preserve the semantic integrity of each modality. The PFMG module reconstructs the feature hierarchy via a progressive hierarchical gating mechanism. This leverages the detailed features from a preceding, higher-resolution level to guide the fusion at the current, lower-resolution level, effectively preserving fine-grained details as features propagate. Through evaluations conducted on the DroneVehicle and VEDAI datasets, our PACGNet sets a new state-of-the-art benchmark, with mAP50 scores reaching 82.2% and 82.1% respectively.
Abstract (translated)
在航空影像中的目标检测是无人机侦察等应用的关键任务。尽管现有方法已经在不同模态之间的特征交互上进行了深入探索，但它们通常依赖于简单的融合策略来进行特征聚合。这引入了两个关键缺陷：容易受到跨模态噪声的影响，并且破坏了特征金字塔的层次结构，从而影响小对象的精细检测能力。 为了解决这一挑战，我们提出了一个名为“金字塔自适应交叉门控网络”（PACGNet）的新架构，该架构旨在骨干网内执行深度融合。为此，我们设计了两个核心组件：对称交叉门控（SCG）模块和金字塔特征感知多模态门控（PFMG）模块。 SCG模块采用双向、对称的“水平”门控机制，以有选择地吸收互补信息，抑制噪声，并保持每种模式的语义完整性。而PFMG模块通过逐步分层的门控机制重构了特征层次结构。它利用前一级高分辨率级别的详细特征来指导当前低分辨率级别的融合过程，从而有效地保留了在特征传递过程中精细级别的细节。 在DroneVehicle和VEDAI数据集上的评估表明，我们的PACGNet设立了一个新的行业标准，在mAP50得分方面分别达到了82.2%和82.1%，显著提升了目标检测的精度。
URL
https://arxiv.org/abs/2512.18291
