发表机构
CSSC Systems Engineering Research Institute（中国船舶集团有限公司系统工程研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对单阶段3D目标检测器采用相同特征完成不同任务的问题，提出TADP方法，通过三重特征细化聚合模块等组件提升性能，在KITTI数据集上汽车类mAP达80.91%，优于诸多先进方法。
AI 中文摘要
大多数单阶段3D目标检测器采用相同的提取特征完成不同任务，但无法将特征投影到对所有任务都自适应的公共空间。为解决该问题，本文提出一种面向单阶段3D目标检测的新型任务感知可变形预测（TADP）方法：首先设计三重特征细化聚合模块自适应提取三级特征；此外，设计多尺度特征聚合模块以尺度感知方式融合多尺度特征；最后，采用所设计的即插即用型任务感知变形头对各任务的预测进行变形，该变形头可感知各任务的侧重点与交互，本文还设计了三种不同的变形模块。实验结果表明，所提变形头在其他检测方法上也表现良好；在KITTI数据集上的实验显示，汽车类别的mAP为80.91%，超过了KITTI基准上的诸多先进方法。
英文摘要
Most single-stage 3D object detectors complete different tasks with the same extracted features. Nevertheless, it is impossible to project features into a common space that is adaptive for all the tasks. We present a novel task-aware deformable prediction (TADP) method for single-stage 3D object detection to solve this problem. Firstly, a triple feature refinement aggregation module is designed to extract three-level features adaptively. Additionally, we design the multi-scale feature aggregation block to fuse multi-scale features in a scale-aware manner. Finally, the prediction of each task is deformed with the designed plug-and-play task-aware deformation head. It can percept the emphasis and interaction of each task. We also designed three different deformation modules. The experimental results demonstrate that the proposed deformation head shows good results on other detection methods. The experimental results on the KITTI dataset demonstrate that the car mAP is 80.91%, surpassing many state-of-the-art methods on the KITTI benchmark.
CommentsAccepted to the 2023 IEEE Intelligent Vehicles Symposium (IV 2023)
