论文标题
CIA-SSD：从点云中自信的IOU Aware单阶段对象检测器
CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud
论文作者
论文摘要
用于将对象定位在点云中的现有单阶段探测器通常将对象定位和类别分类视为单独的任务，因此本地化准确性和分类置信度可能无法很好地保持一致。为了解决此问题，我们提出了一个新的单阶段检测器，名为“自信Iou-Aware单阶段对象检测器（CIA-SSD）”。首先，我们设计了轻巧的空间语义特征聚合模块，以适应融合的高级抽象语义特征和低级空间特征，以准确预测边界框和分类置信度。同样，通过我们设计的IOU Aware置信度整流模块，预测的置信度得到了进一步纠正，以使置信度与本地化精度更加一致。基于纠正的置信度，我们进一步制定了距离变化的IOU加权NMS，以获得更平滑的回归并避免冗余预测。我们在KITTI测试集中的3D CAR检测中实验CIA-SSD，并表明它在官方排名度量（中度AP 80.28％）和32 fps推理速度方面取得了最高性能，优于所有先前的单阶段检测器。该代码可在https://github.com/vegeta2020/cia-ssd上找到。
Existing single-stage detectors for locating objects in point clouds often treat object localization and category classification as separate tasks, so the localization accuracy and classification confidence may not well align. To address this issue, we present a new single-stage detector named the Confident IoU-Aware Single-Stage object Detector (CIA-SSD). First, we design the lightweight Spatial-Semantic Feature Aggregation module to adaptively fuse high-level abstract semantic features and low-level spatial features for accurate predictions of bounding boxes and classification confidence. Also, the predicted confidence is further rectified with our designed IoU-aware confidence rectification module to make the confidence more consistent with the localization accuracy. Based on the rectified confidence, we further formulate the Distance-variant IoU-weighted NMS to obtain smoother regressions and avoid redundant predictions. We experiment CIA-SSD on 3D car detection in the KITTI test set and show that it attains top performance in terms of the official ranking metric (moderate AP 80.28%) and above 32 FPS inference speed, outperforming all prior single-stage detectors. The code is available at https://github.com/Vegeta2020/CIA-SSD.
