TADP: Task-Aware Deformable Prediction for Single-Stage 3D Object Detection

2026-08-27

AI Summary

提出一种任务感知的可变形预测方法(TADP)，通过自适应特征提取和多尺度特征融合解决单阶段3D目标检测中不同任务适应性问题。

Abstract

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.

Problem

• single-stage 3D object detection
• feature extraction
• task-aware

Innovation

• task-aware deformable prediction
• triple feature refinement aggregation
• multi-scale feature aggregation