Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism

By Zanjia Tong, Yuhang Chen, Zewei Xu, Rongwei Yu. arXiv.org, 2023

971 citations recorded by the source corpus.

The loss function for bounding box regression (BBR) is essential to object detection. Its good definition will bring significant performance improvement to the model. Most existing works assume that the examples in the training data are high-quality and focus on strengthening the fitting ability of BBR loss. If we blindly strengthen BBR on low-quality examples, it will jeopardize localization performance. Focal-EIoU v1 was proposed to solve this problem, but due to its static focusing mechanism (FM), the potential of non-monotonic FM was not fully exploited. Based on this idea, we propose an IoU-based loss with a dynamic non-monotonic FM named Wise-IoU (WIoU). The dynamic non-monotonic FM uses the outlier degree instead of IoU to evaluate the quality of anchor boxes and provides a wise gradient gain allocation strategy. This strategy reduces the competitiveness of high-quality anchor boxes while also reducing the harmful gradient generated by low-quality examples. This allows WIoU to focus on ordinary-quality anchor boxes and improve the detector's overall performance. When WIoU is applied to the state-of-the-art real-time detector YOLOv7, the AP-75 on the MS-COCO dataset is improved from 53.03% to 54.50%. Code is available at https://github.com/Instinct323/wiou.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f2a42960b362bc673638643257d65c309b7324dd

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hanyu Hong
2. Pei An
3. G. Wang
4. Yanfei Chen
5. Tiange Huang
6. Jinghu Hu
7. Jun Liu
8. Alex ChiChung Kot

In Computer Vision and Pattern Recognition

1. Hanyu Hong
2. Pei An
3. G. Wang
4. Yanfei Chen
5. Tiange Huang
6. Jinghu Hu
7. Jun Liu
8. Hossein Rahmani

Citations in the corpus

• UAV-YOLOv8: A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography Scenarios (2023, methodology): “• We incorporate WIoU v3 [31] in our bounding box regression loss, which employs a dynamic non-monotonic mechanism to design a more reasonable gradient gain allocation strategy.”