Fig. 3: Performance of the YOLOX model on the held-out test dataset with different IoU-Ts. | Nature Communications

Fig. 3: Performance of the YOLOX model on the held-out test dataset with different IoU-Ts.

From: A deep-learning-based framework for identifying and localizing multiple abnormalities and assessing cardiomegaly in chest X-ray

Fig. 3

a AP values of 14 abnormalities with an IoU-T of 0.5, b AP values of 14 abnormalities with an IoU-T of 0.3, c AP values of 14 abnormalities with an IoU-T of 0.1. AP: average precision, IoU-T: intersection over union threshold. (Source data are provided as a Source Data file.).

Back to article page