Focal Iou loss: More attentive learning for bounding box regression
Yuan Liao, Peixia Cao
Abstract
In this paper, we investigate a more efficient IoU loss based bounding box localization mechanism on top of end-to-end target detection frameworks to further improve the regression accuracy of object detection methods. Aiming at the limited spatial perception ability of deep convolution features, this paper proposes an optimization strategy by combining shallow spatial feature feed-forward mechanism (SSFF) with focal IoU loss function for bounding box regression tasks in target detection. This strategy firstly constructs a channel to transfer important location information in shallow spatial features to deep spatial features to reduce the loss of spatial details. Secondly, it constructs a focal IoU loss function based on the IoU loss, which dynamically adjusts loss weights according to the regression difficulty of different bounding boxes, to improve the positioning ability of regression networks on difficult bounding boxes. The experimental results show that the proposed methods can effectively improve the regression accuracy of target detection models.