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 (e.g., L 1 or L 2 ) is often adopted as the loss function to minimize the discrepency 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 [1] and [2]. 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 [3] benchmark.

HUMANNET—A Two-Tiered Deep Neural Network Architecture for Self-Occluding Humanoid Pose Reconstruction

“…In order to evaluate the accuracy of our clipping node we used Jaccards index [60][61][62] to compare the quality of our three-dimentional bounding boxes, which is widely adopted as a metric to compare bounding boxes. Our results (seen in Figure 4) indicate that for most of our anchors but one our I ∩ U ≈ 80%, with overall accuracy being 79.07%, with some clipping error was able to be improved by slightly expanding the bounding boxes thus potentially improving bounding boxes which were very close to ground truth.…”

One-Stage Anchor-Free 3D Vehicle Detection from LiDAR Sensors

“…To jointly train the regression branches, we introduce the IoU layer in the detector and calculate the auxiliary loss. After decoding the bounding box (x, y, z, w, l, h, θ) of the target from the regression branches, the network applies Equation ( 8) to measure the 3D IoU [37]:…”

Confidence-Aware Object Detection Based on MobileNetv2 for Autonomous Driving

“…They are not absolutely equivalent. To compensate for the gap between the smooth L 1 loss and IoU, Zhou et al proposed IoU loss [19], which regresses the offset between the location of the object's center and the center of an anchor box and then uses the width and height of the anchor box to predict the relative scale of the predicted object boxes. Apart from IoU loss, Generalized-IoU (GIoU) loss [2], Distance-IoU (DIoU) loss [20], and Complete-IoU (CIoU) loss [20] were proposed, which can be seen as extending IoU loss.…”