スパース性不変特徴の学習による3D物体検出の汎化性能向上
Improving Generalization Ability for 3D Object Detection by Learning Sparsity-invariant Features
単一のソースドメインから、異なるセンサ構成やシーン分布を持つターゲットドメインへ汎化する3D物体検出の手法を提案。検出器の信頼度に基づき点群をサブサンプリングし、teacher-studentフレームワークでBEV特徴を整列させる。
著者: Hsin-Cheng Lu, Chung-Yi Lin, Winston H. Hsu
分類: cs.CV, cs.RO
原文アブストラクト
In autonomous driving, 3D object detection is essential for accurately identifying and tracking objects. Despite the continuous development of various technologies for this task, a significant drawback is observed in most of them-they experience substantial performance degradation when detecting objects in unseen domains. In this paper, we propose a method to improve the generalization ability for 3D object detection on a single domain. We primarily focus on generalizing from a single source domain to target domains with distinct sensor configurations and scene distributions. To learn sparsity-invariant features from a single source domain, we selectively subsample the source data to a specific beam, using confidence scores determined by the current detector to identify the density that holds utmost importance for the detector. Subsequently, we employ the teacher-student framework to align the Bird's Eye View (BEV) features for different point clouds densities. We also utilize feature content alignment (FCA) and graph-based embedding relationship alignment (GERA) to instruct the detector to be domain-agnostic. Extensive experiments demonstrate that our method exhibits superior generalization capabilities compared to other baselines. Furthermore, our approach even outperforms certain domain adaptation methods that can access to the target domain data.
