Rethinking IoU-based Optimization for Single-stage 3D Object Detection
- URL: http://arxiv.org/abs/2207.09332v2
- Date: Wed, 20 Jul 2022 06:27:31 GMT
- Title: Rethinking IoU-based Optimization for Single-stage 3D Object Detection
- Authors: Hualian Sheng, Sijia Cai, Na Zhao, Bing Deng, Jianqiang Huang,
Xian-Sheng Hua, Min-Jian Zhao, Gim Hee Lee
- Abstract summary: We propose a Rotation-Decoupled IoU (RDIoU) method that can mitigate the rotation-sensitivity issue.
Our RDIoU simplifies the complex interactions of regression parameters by decoupling the rotation variable as an independent term.
- Score: 103.83141677242871
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Since Intersection-over-Union (IoU) based optimization maintains the
consistency of the final IoU prediction metric and losses, it has been widely
used in both regression and classification branches of single-stage 2D object
detectors. Recently, several 3D object detection methods adopt IoU-based
optimization and directly replace the 2D IoU with 3D IoU. However, such a
direct computation in 3D is very costly due to the complex implementation and
inefficient backward operations. Moreover, 3D IoU-based optimization is
sub-optimal as it is sensitive to rotation and thus can cause training
instability and detection performance deterioration. In this paper, we propose
a novel Rotation-Decoupled IoU (RDIoU) method that can mitigate the
rotation-sensitivity issue, and produce more efficient optimization objectives
compared with 3D IoU during the training stage. Specifically, our RDIoU
simplifies the complex interactions of regression parameters by decoupling the
rotation variable as an independent term, yet preserving the geometry of 3D
IoU. By incorporating RDIoU into both the regression and classification
branches, the network is encouraged to learn more precise bounding boxes and
concurrently overcome the misalignment issue between classification and
regression. Extensive experiments on the benchmark KITTI and Waymo Open Dataset
validate that our RDIoU method can bring substantial improvement for the
single-stage 3D object detection.
Related papers
- DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection [42.07920565812081]
We propose a novel post-training weight pruning scheme for 3D object detection.
It determines redundant parameters in the pretrained model that lead to minimal distortion in both locality and confidence.
This framework aims to minimize detection distortion of network output to maximally maintain detection precision.
arXiv Detail & Related papers (2024-07-02T09:33:32Z) - GOOD: General Optimization-based Fusion for 3D Object Detection via
LiDAR-Camera Object Candidates [10.534984939225014]
3D object detection serves as the core basis of the perception tasks in autonomous driving.
Good is a general optimization-based fusion framework that can achieve satisfying detection without training additional models.
Experiments on both nuScenes and KITTI datasets are carried out and the results show that GOOD outperforms by 9.1% on mAP score compared with PointPillars.
arXiv Detail & Related papers (2023-03-17T07:05:04Z) - Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in
Driving Scenes [82.4186966781934]
We introduce a simple, efficient, and effective two-stage detector, termed as Ret3D.
At the core of Ret3D is the utilization of novel intra-frame and inter-frame relation modules.
With negligible extra overhead, Ret3D achieves the state-of-the-art performance.
arXiv Detail & Related papers (2022-08-18T03:48:58Z) - Decoupled IoU Regression for Object Detection [31.9114940121939]
Non-maximum suppression (NMS) is widely used in object detection pipelines for removing duplicated bounding boxes.
Inconsistency between the confidence for NMS and the real localization confidence seriously affects detection performance.
We propose a novel Decoupled IoU Regression model to handle these problems.
arXiv Detail & Related papers (2022-02-02T04:01:11Z) - The KFIoU Loss for Rotated Object Detection [115.334070064346]
In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss.
Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU.
The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
arXiv Detail & Related papers (2022-01-29T10:54:57Z) - ST3D: Self-training for Unsupervised Domain Adaptation on 3D
ObjectDetection [78.71826145162092]
We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised domain adaptation on 3D object detection from point clouds.
Our ST3D achieves state-of-the-art performance on all evaluated datasets and even surpasses fully supervised results on KITTI 3D object detection benchmark.
arXiv Detail & Related papers (2021-03-09T10:51:24Z) - Reinforced Axial Refinement Network for Monocular 3D Object Detection [160.34246529816085]
Monocular 3D object detection aims to extract the 3D position and properties of objects from a 2D input image.
Conventional approaches sample 3D bounding boxes from the space and infer the relationship between the target object and each of them, however, the probability of effective samples is relatively small in the 3D space.
We propose to start with an initial prediction and refine it gradually towards the ground truth, with only one 3d parameter changed in each step.
This requires designing a policy which gets a reward after several steps, and thus we adopt reinforcement learning to optimize it.
arXiv Detail & Related papers (2020-08-31T17:10:48Z) - 3D IoU-Net: IoU Guided 3D Object Detector for Point Clouds [68.44740333471792]
We add a 3D IoU prediction branch to the regular classification and regression branches.
We propose a 3D IoU-Net with IoU sensitive feature learning and an IoU alignment operation.
The experimental results on the KITTI car detection benchmark show that 3D IoU-Net with IoU perception achieves state-of-the-art performance.
arXiv Detail & Related papers (2020-04-10T09:24:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.