DPDETR：用于红外-可见光目标检测的解耦位置检测Transformer
DPDETR: Decoupled Position Detection Transformer for Infrared-Visible Object Detection
AI总结：
针对红外-可见光目标检测中的模态失配难题，提出DPDETR模型，通过解耦位置定义、交叉注意力模块、查询解耦解码器及对比去噪训练，实现更精准的双模态目标检测，性能优于现有最优方法。
摘要：
红外-可见光目标检测旨在利用红外与可见光图像对的互补信息实现鲁棒的目标检测。然而，普遍存在的模态失配问题带来了两大挑战：失配的互补特征难以融合，且现有方法在失配条件下无法可靠地在两种模态中定位目标。本文提出了解耦位置检测Transformer（Decoupled Position Detection Transformer，DPDETR）以解决这些问题。具体而言，我们显式定义了目标类别、可见光模态位置与红外模态位置，使网络能够学习内在关联并输出目标在两种模态中的可靠位置。为可靠融合失配的目标特征，我们提出了解耦位置多光谱交叉注意力模块，该模块在红外与可见光参考位置的约束下，自适应采样并聚合多光谱互补特征。此外，我们设计了查询解耦的多光谱解码器结构，以解决任务中三类目标信息的特征聚焦冲突，并提出解耦位置对比去噪训练策略，增强DPDETR学习解耦位置的能力。在DroneVehicle和KAIST数据集上的实验表明，该方法相比其他现有最优方法取得了显著提升。代码将发布于https://github.com/gjj45/DPDETR。
英文摘要：
Infrared-visible object detection aims to achieve robust object detection by leveraging the complementary information of infrared and visible image pairs. However, the commonly existing modality misalignment problem presents two challenges: fusing misalignment complementary features is difficult, and current methods cannot reliably locate objects in both modalities under misalignment conditions. In this paper, we propose a Decoupled Position Detection Transformer (DPDETR) to address these issues. Specifically, we explicitly define the object category, visible modality position, and infrared modality position to enable the network to learn the intrinsic relationships and output reliably positions of objects in both modalities. To fuse misaligned object features reliably, we propose a Decoupled Position Multispectral Cross-attention module that adaptively samples and aggregates multispectral complementary features with the constraint of infrared and visible reference positions. Additionally, we design a query-decoupled Multispectral Decoder structure to address the the conflict in feature focus among the three kinds of object information in our task and propose a Decoupled Position Contrastive DeNoising Training strategy to enhance the DPDETR's ability to learn decoupled positions. Experiments on DroneVehicle and KAIST datasets demonstrate significant improvements compared to other state-of-the-art methods. The code will be released at https://github.com/gjj45/DPDETR
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
