IoU Loss for 2D/3D Object Detection

Abstract

In 2D/3D object detection task, Intersection-over-Union (IoU) has been widely employed as an evaluation metric to evaluate the performance of different detectors in the testing stage. However, during the training stage, the common distance loss (\eg, $L_1$ or $L_2$) is often adopted as the loss function to minimize the discrepancy between the predicted and ground truth Bounding Box (Bbox). To eliminate the performance gap between training and testing, the IoU loss has been introduced for 2D object detection in \cite{yu2016unitbox} and \cite{rezatofighi2019generalized}. Unfortunately, all these approaches only work for axis-aligned 2D Bboxes, which cannot be applied for more general object detection task with rotated Bboxes. To resolve this issue, we investigate the IoU computation for two rotated Bboxes first and then implement a unified framework, IoU loss layer for both 2D and 3D object detection tasks. By integrating the implemented IoU loss into several state-of-the-art 3D object detectors, consistent improvements have been achieved for both bird-eye-view 2D detection and point cloud 3D detection on the public KITTI benchmark.

arXiv commentAccepted by international conference on 3d vision 2019

References in corpus (4)

• DSSD : Deconvolutional Single Shot Detector
• Deep Continuous Fusion for Multi-Sensor 3D Object Detection
• Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection
• IPOD: Intensive Point-based Object Detector for Point Cloud

Cited by in corpus (6)

• SCPM-Net: An Anchor-free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matching
• HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
• Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
• EllipseNet: Anchor-Free Ellipse Detection for Automatic Cardiac Biometrics in Fetal Echocardiography
• DV-Det: Efficient 3D Point Cloud Object Detection with Dynamic Voxelization
• Boundary-Aware Dense Feature Indicator for Single-Stage 3D Object Detection from Point Clouds