Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box

TL;DR

Inner-IoU introduces a novel IoU loss method using auxiliary bounding boxes scaled according to sample IoU, improving convergence speed and detection accuracy across different detectors and datasets.

Contribution

The paper proposes Inner-IoU, a new IoU loss that adaptively scales auxiliary bounding boxes based on sample IoU, enhancing generalization and performance in bounding box regression.

Findings

Inner-IoU accelerates convergence in bounding box regression.

It improves detection performance across various detectors and datasets.

The method demonstrates strong generalization and effectiveness.

Abstract

With the rapid development of detectors, Bounding Box Regression (BBR) loss function has constantly updated and optimized. However, the existing IoU-based BBR still focus on accelerating convergence by adding new loss terms, ignoring the limitations of IoU loss term itself. Although theoretically IoU loss can effectively describe the state of bounding box regression,in practical applications, it cannot adjust itself according to different detectors and detection tasks, and does not have strong generalization. Based on the above, we first analyzed the BBR model and concluded that distinguishing different regression samples and using different scales of auxiliary bounding boxes to calculate losses can effectively accelerate the bounding box regression process. For high IoU samples, using smaller auxiliary bounding boxes to calculate losses can accelerate convergence, while larger auxiliary bounding boxes are suitable for low IoU samples. Then, we propose Inner-IoU loss, which calculates IoU loss through auxiliary bounding boxes. For different datasets and detectors, we introduce a scaling factor ratio to control the scale size of the auxiliary bounding boxes for calculating losses. Finally, integrate Inner-IoU into the existing IoU-based loss functions for simulation and comparative experiments. The experiment result demonstrate a further enhancement in detection performance with the utilization of the method proposed in this paper, verifying the effectiveness and generalization ability of Inner-IoU loss. Code is available at https://github.com/malagoutou/Inner-IoU.