Table 4 Comparison between the performance of yolov5s trained using its own loss (\({\mathcal{L}}_{IoU}\)) as well as \({\mathcal{L}}_{GIoU}\), \({\mathcal{L}}_{DIoU}\), \({\mathcal{L}}_{CIoU}\) and proposed scheme \({\mathcal{L}}_{IoAverage}\) losses. The results are reported on the test dataset of pascal voc 2007
From: Vehicle logo detection using an IoAverage loss on dataset VLD100K-61
Loss/evaluation | mAP0.5 | mAP0.5:0.95 |
|---|---|---|
\({\mathcal{L}}_{IoU}\) | 0.598 | 0.379 |
\({\mathcal{L}}_{GIoU}\) Relative improv. % | 0.601 0.502% | 0.382 0.792% |
\({\mathcal{L}}_{DIoU}\) Relative improv. % | 0.599 0.167% | 0.379 0.0% |
\({\mathcal{L}}_{CIoU}\) Relative improv. % | 0.596 − 0.334% | 0.38 0.264% |
\({\mathcal{L}}_{IoAverage}\) Relative improv. % | 0.641 7.191% | 0.496 30.87% |