Hardness-Aware Scene Synthesis for Semi-Supervised 3D Object Detection
3D物体检测的目标是恢复有关物体的3D信息，并作为自动驾驶感知的基本任务。其性能在很大程度上取决于标注训练数据的规模，然而为点云数据获得高质量注释的成本很高。虽然传统方法将伪标签作为未标注样本的补充用于训练，但3D点云数据的结构使物体和背景的组合变得容易，从而合成真实场景。为了提高检测模型的泛化能力，我们提出了一个基于难度的场景生成（HASS）方法，用于生成自适应的合成场景。我们为未标注的对象获得伪标签，并生成具有不同物体和背景组合的场景。由于场景合成对伪标签的质量敏感，我们进一步提出了一个基于难度的策略，以减少低质量伪标签的影响，并保持动态伪数据库，以确保合成场景的多样性和质量。在广泛使用的KITTI和Waymo数据集上的实验结果表明，所提出的HASS方法具有优越性，其在3D物体检测方面超过了现有的半监督学习方法。代码：https://this URL。
3D object detection aims to recover the 3D information of concerning objects and serves as the fundamental task of autonomous driving perception. Its performance greatly depends on the scale of labeled training data, yet it is costly to obtain high-quality annotations for point cloud data. While conventional methods focus on generating pseudo-labels for unlabeled samples as supplements for training, the structural nature of 3D point cloud data facilitates the composition of objects and backgrounds to synthesize realistic scenes. Motivated by this, we propose a hardness-aware scene synthesis (HASS) method to generate adaptive synthetic scenes to improve the generalization of the detection models. We obtain pseudo-labels for unlabeled objects and generate diverse scenes with different compositions of objects and backgrounds. As the scene synthesis is sensitive to the quality of pseudo-labels, we further propose a hardness-aware strategy to reduce the effect of low-quality pseudo-labels and maintain a dynamic pseudo-database to ensure the diversity and quality of synthetic scenes. Extensive experimental results on the widely used KITTI and Waymo datasets demonstrate the superiority of the proposed HASS method, which outperforms existing semi-supervised learning methods on 3D object detection. Code: this https URL.
https://arxiv.org/abs/2405.17422
https://arxiv.org/pdf/2405.17422.pdf