I implemented an image segmentation pipeline and I trained it on the DICOM dataset. I compared the results of the model with manual segmentation to find the accuracy. Is there other methods for evaluation?



Martin Thoma: A Survey of Semantic Segmentation, Section III

Subsection A is about metrics and B is about datasets.

Metrics include: accuracy, IoU, frequency weighted IoU, F-beta score, speed, ...


The paper referenced by Martin Thoma is the go-to for semantic segmentation. However I will also like to add the Panoptic Segmentation metric as an aggregated method to measure both the detection task and segmentation task of the model.

It is a very well-known and widely used metric since it is the standard metric for COCO dataset (segmentation)

This is the paper where the metric is proposed.

And here is the metric:

enter image description here


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.