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

TL;DR

Wise-IoU introduces a dynamic focusing mechanism for bounding box regression loss that adaptively emphasizes anchor boxes based on their outlier degree, enhancing object detection performance.

Contribution

The paper proposes Wise-IoU, a novel IoU-based loss with a dynamic non-monotonic focusing mechanism that better exploits non-monotonic gradients for improved localization.

Findings

Improves AP-75 on MS-COCO from 53.03% to 54.50%.

Reduces harmful gradients from low-quality examples.

Focuses training on ordinary-quality anchor boxes.

Abstract

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.