Rethinking IoU-based Optimization for Single-stage 3D Object Detection

07/19/2022
by   Hualian Sheng, et al.
0

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.

READ FULL TEXT

page 5

page 19

research
09/24/2021

RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detection

We classify the discontinuity of loss in both five-param and eight-param...
research
09/03/2019

Object Viewpoint Classification Based 3D Bounding Box Estimation for Autonomous Vehicles

3D object detection is one of the most important tasks for the perceptio...
research
03/22/2021

Optimization for Oriented Object Detection via Representation Invariance Loss

Arbitrary-oriented objects exist widely in natural scenes, and thus the ...
research
03/14/2018

Rotation-Sensitive Regression for Oriented Scene Text Detection

Text in natural images is of arbitrary orientations, requiring detection...
research
05/29/2019

Disentangling Monocular 3D Object Detection

In this paper we propose an approach for monocular 3D object detection f...
research
12/16/2021

Toward Minimal Misalignment at Minimal Cost in One-Stage and Anchor-Free Object Detection

Common object detection models consist of classification and regression ...
research
12/11/2019

Learning from Noisy Anchors for One-stage Object Detection

State-of-the-art object detectors rely on regressing and classifying an ...

Please sign up or login with your details

Forgot password? Click here to reset