TANet: Robust 3D Object Detection from Point Clouds with Triple Attention

By Zhe Liu, Xin Zhao, Tengteng Huang, Ruolan Hu, Yu Zhou, Xiang Bai. AAAI Conference on Artificial Intelligence, 2019

422 citations recorded by the source corpus.

In this paper, we focus on exploring the robustness of the 3D object detection in point clouds, which has been rarely discussed in existing approaches. We observe two crucial phenomena: 1) the detection accuracy of the hard objects, e.g., Pedestrians, is unsatisfactory, 2) when adding additional noise points, the performance of existing approaches decreases rapidly. To alleviate these problems, a novel TANet is introduced in this paper, which mainly contains a Triple Attention (TA) module, and a Coarse-to-Fine Regression (CFR) module. By considering the channel-wise, point-wise and voxel-wise attention jointly, the TA module enhances the crucial information of the target while suppresses the unstable cloud points. Besides, the novel stacked TA further exploits the multi-level feature attention. In addition, the CFR module boosts the accuracy of localization without excessive computation cost. Experimental results on the validation set of KITTI dataset demonstrate that, in the challenging noisy cases, i.e., adding additional random noisy points around each object, the presented approach goes far beyond state-of-the-art approaches. Furthermore, for the 3D object detection task of the KITTI benchmark, our approach ranks the first place on Pedestrian class, by using the point clouds as the only input. The running speed is around 29 frames per second.

Subfields: Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/d8fc74db276e3f2630fcf95e26b0f82ab73d3d87

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

In Geology

Citations in the corpus

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 [”
Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection (2020, methodology): “…on point clouds into point-based (Shi, Wang, and Li 2019; Yang et al. 2019; Yilun Chen and Jia 2019; Yang et al. 2020; Shi et al. 2020a) methods and voxel-based (Zhou and Tuzel 2018; Yan, Mao, and Li 2018; Yang, Luo, and Urtasun 2018; Simon et al. 2018; Lang et al. 2019; Liu et al. 2020b) meth-ods.”
CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud (2020, methodology): “TANet (Liu et al. 2020) presents a triple attention module embedded in voxel feature extraction and combines it with a proposed cascaded reﬁne-ment network.”
Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review (2020, background): “TANet [Liu et al., 2020c] proposed a Triple Attention (TA) module and a Coarse-to-Fine Regression (CFR) module, which focuses on the 3D detection of hard objects and the robustness to noisy points.”
SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud (2021, methodology): “For single-stage detectors, Point-GNN [26] adapts a graph neural network to obtain a more compact representation of point cloud, while TANet [17] designs a delicate triple attention module to consider the feature-wise relation.”
EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection (2020, neutral): “67 TANet [21] L 84.”
An End-to-End Transformer Model for 3D Object Detection (2021, methodology): “Attention based methods have been used for building 3D point representations for retrieval [87], outdoor 3D detection [29, 36, 86], object classiﬁcation [83].”
Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds (2022, neutral): “Although remarkable progress has been achieved recently [2, 3, 7, 11, 24, 39, 53, 54], these”