EMSANet
EMSANet copied to clipboard
About the inference metric
Dear authors,
Hello, thank you for your great work. I have a question regarding the inference outputs. Could you please tell me how the two metrics, 'valid_panoptic_deeplab_semantic_miou' and 'valid_semantic_miou' are different?
'valid_semantic_miou' is before and 'valid_panoptic_deeplab_semantic_miou' is after merging semantic and instance predictions in order to derive the panoptic prediction. Merging both puts more focus on instances and assigns a single semantic class to all pixels assigned to an instance. This can overrule the semantic predictions and, thus, may change mIoU.