SEGT: A General Spatial Expansion Group Transformer for nuScenes Lidar-based Object Detection Task
This work addresses the problem of accurate object detection in autonomous driving systems, representing an incremental improvement in a domain-specific task.
The paper tackles 3D object detection from lidar point clouds on the nuScenes dataset by proposing a transformer-based framework with spatial expansion strategies and group attention, achieving state-of-the-art results with an NDS score of 73.9 without TTA and 74.5 with TTA.
In the technical report, we present a novel transformer-based framework for nuScenes lidar-based object detection task, termed Spatial Expansion Group Transformer (SEGT). To efficiently handle the irregular and sparse nature of point cloud, we propose migrating the voxels into distinct specialized ordered fields with the general spatial expansion strategies, and employ group attention mechanisms to extract the exclusive feature maps within each field. Subsequently, we integrate the feature representations across different ordered fields by alternately applying diverse expansion strategies, thereby enhancing the model's ability to capture comprehensive spatial information. The method was evaluated on the nuScenes lidar-based object detection test dataset, achieving an NDS score of 73.9 without Test-Time Augmentation (TTA) and 74.5 with TTA, demonstrating the effectiveness of the proposed method. Notably, our method ranks the 1st place in the nuScenes lidar-based object detection task.