Focaler-IoU: More Focused Intersection over Union Loss

TL;DR

This paper introduces Focaler-IoU, a novel loss function for bounding box regression in object detection that emphasizes difficult samples to enhance detection accuracy across various tasks.

Contribution

The paper proposes Focaler-IoU, a new loss function that improves bounding box regression by focusing on sample difficulty, addressing limitations of existing geometric-based methods.

Findings

Enhanced detection performance across multiple detectors

Improved accuracy in different object detection tasks

Effective focus on challenging samples during training

Abstract

Bounding box regression plays a crucial role in the field of object detection, and the positioning accuracy of object detection largely depends on the loss function of bounding box regression. Existing researchs improve regression performance by utilizing the geometric relationship between bounding boxes, while ignoring the impact of difficult and easy sample distribution on bounding box regression. In this article, we analyzed the impact of difficult and easy sample distribution on regression results, and then proposed Focaler-IoU, which can improve detector performance in different detection tasks by focusing on different regression samples. Finally, comparative experiments were conducted using existing advanced detectors and regression methods for different detection tasks, and the detection performance was further improved by using the method proposed in this paper.Code is available at \url{https://github.com/malagoutou/Focaler-IoU}.