CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud

By Wu Zheng, Weiliang Tang, Sijin Chen, Li Jiang, Chi-Wing Fu. 2020

340 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection (2021, background): “…and Tuzel 2018; Chen et al. 2019; Lang et al. 2019; Qi et al. 2019; Shi, Wang, and Li 2019; Yang et al. 2019; Zhou et al. 2019; Yang et al. 2020; Zheng et al. 2021) are proposed and have shown impressive performance in localizing and categorizing objects of interest in the point cloud of a…”
Focal Sparse Convolutional Networks for 3D Object Detection (2022, background): “, the R-CNN family [11, 28, 36, 37] and the SSD family [17, 51, 60, 61].”
3D Object Detection for Autonomous Driving: A Survey (2021, neutral): “+ TANet [76], AAAI′20 + VeloFCN [48], RSS′16 + SPG [77], ICCV′21 + PIXOR [49], CVPR′18 + CenterPoint [23], CVPR′21 + VoxelNet [24], CVPR′18 + BtcDet [10], AAAI′22 + SECOND [25], Sensors′18 + PointPillars [6], CVPR′19 + CIA-SSD [26], AAAI′21 + SE-SSD [27], CVPR′21 + Voxel R-CNN [28], AAAI′21 + CT3D [”
Improving 3D Object Detection with Channel-wise Transformer (2021, methodology): “is the voxel-based methods [33, 27, 39] which use 3D convolutional kernels to gather information from neighboring voxels.”
Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds (2022, neutral): “16 - - - - - - 25 CIA-SSD [58] AAAI 2021 1-stage 89.”
SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud (2021, methodology): “Architecture of Teacher & Student SSD The model has the same structure as [35] to efficiently encode point clouds, but we remove the Confidence Function and DI-NMS.”