让3D目标检测任务各自用适配的特征，提升精度
TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection
- 为不同检测任务设计自适应特征提取与变形预测头
- 在KITTI上汽车类检测准确率达80.91%，超越多数方法
- 适合需要高精度单阶段3D检测的自动驾驶场景
大多数单阶段3D目标检测器使用相同的特征完成不同任务。然而，将特征投影到对所有任务都适应的统一空间是不可行的。本文提出一种新型任务感知可变形预测（TADP）方法，解决该问题。首先，设计三层次特征精炼聚合模块以自适应提取多级特征；其次，引入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，通过即插即用的任务感知变形头对各任务预测进行变形，使其能感知任务间的关注点与交互。我们还设计了三种不同的变形模块。实验表明，所提变形头在其他检测方法上也表现良好。在KITTI数据集上的结果表明，汽车类别mAP达到80.91%，超越多个当前最优方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。