Jun 13, 2023 · Generally, object detection needs two loss functions, one for object classification and the other for bounding box regression. This article will focus on IoU loss functions (GIoU loss, DIoU loss, and CIoU loss). But first, we will gain an intuitive understanding of the loss function for object detection in general.

Aug 11, 2019 · 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.

Sep 28, 2022 · We reveal the flaws of ℓ n -norm and IOU-based losses for object detection. We design a regression version of focal loss to emphasize the most promising anchors. We conduct extensive experiments to validate the superiority of the proposed methods.

Mar 24, 2020 · This phenomenon is found and explained by Zheng et al. [6] in which they propose a better version of IoU Loss called Distance-IoU Loss (DIoU) and the complete form Complete-IoU Loss (CIoU).

Object detection neural networks commonly use ℓ1 ℓ 1 -norm or ℓ2 ℓ 2 -norm for their cost function (aka. loss function). Our work shows that there is not a strong correlation between minimizing these commonly used losses and improving their IoU value.

Feb 25, 2019 · Intersection over Union (IoU) is the most popular evaluation metric used in the object detection benchmarks. However, there is a gap between optimizing the commonly used distance losses for regressing the parameters of a bounding box and maximizing this metric value. The optimal objective for a metric is the metric itself.

Mar 8, 2021 · Distance-IoU (DIoU) loss uses the normalized distance between the predicted box and ground truth and converges much faster in training than IoU and GIoU losses.

Jan 20, 2025 · In the early stages of object detection models, L1 (Mean Absolute Error) and L2 (Mean Squared Error) losses were commonly used to calculate the difference between the predicted bounding box and the...

In this paper, we explored the IoU calcula-tion between two rotated Bboxes first and then implemented a unified IoU loss function which can be used for both axis-aligned and rotated 2D object detection. In addition, the new IoU loss can be also applied for 3D object detection which has only one freedom of degree for orientation.

Apr 1, 2022 · IoU-balanced localization loss up-weights the gradients of examples with high IoU while suppressing the gradients of examples with low IoU, making the model more powerful for accurate localization.