Submission details of abc

Name abc
Paper Link N/A
Code Link N/A
Input N/A
Runtime 0.026 s
Environment 1 GPU (GTX 1080Ti)
Abstract In this paper, we focus on exploring the robustness of the3D object detection in point clouds, which has been rarelydiscussed in existing approaches. We observe two crucialphenomena: 1) the detection accuracy of the hard objects,e.g., Pedestrians, is unsatisfactory, 2) when adding additionalnoise points, the performance of existing approaches de-creases rapidly. To alleviate these problems, a novel TANet isintroduced in this paper, which mainly contains a Triple At-tention (TA) module, and a Coarse-to-Fine Regression (CFR)module. By considering the channel-wise, point-wise andvoxel-wise attention jointly, the TA module enhances the cru-cial information of the target while suppresses the unsta-ble cloud points. Besides, the novel stacked TA further ex-ploits the multi-level feature attention. In addition, the CFRmodule boosts the accuracy of localization without excessivecomputation cost. Experimental results on the validation setof KITTI dataset demonstrate that, in the challenging noisycases, i.e., adding additional random noisy points around eachobject, the presented approach goes far beyond state-of-the-art approaches. Furthermore, for the 3D object detection taskof the KITTI benchmark, our approach ranks the first place onPedestrian class, by using the point clouds as the only input.The running speed is around 29 frames per second.

Detailed results

Overall precision/recall curve

Per-sequence results

sequence name AP
cubberly-auditorium-2019-04-22_1 0
discovery-walk-2019-02-28_0 0
discovery-walk-2019-02-28_1 0
food-trucks-2019-02-12_0 0
gates-ai-lab-2019-04-17_0 0
gates-basement-elevators-2019-01-17_0 0
gates-foyer-2019-01-17_0 0
gates-to-clark-2019-02-28_0 0
hewlett-class-2019-01-23_0 0
hewlett-class-2019-01-23_1 0
huang-2-2019-01-25_1 0
huang-intersection-2019-01-22_0 0
indoor-coupa-cafe-2019-02-06_0 0
lomita-serra-intersection-2019-01-30_0 0
meyer-green-2019-03-16_1 0
nvidia-aud-2019-01-25_0 0
nvidia-aud-2019-04-18_1 0
nvidia-aud-2019-04-18_2 0
outdoor-coupa-cafe-2019-02-06_0 0
quarry-road-2019-02-28_0 0
serra-street-2019-01-30_0 0
stlc-111-2019-04-19_1 0
stlc-111-2019-04-19_2 0
tressider-2019-03-16_2 0
tressider-2019-04-26_0 0
tressider-2019-04-26_1 0
tressider-2019-04-26_3 0
total 0.0