Improve instance segmentation performance by learning about all possible scenarios where your algorithm application fails to deliver the expected outcomes.
We take a look at four special cases where your instance segmentation algorithm application is underperforming and offer you practical solutions to the occurring issues.
...
In practice, you want to find out how well your algorithm application performs on images showing actual object instances.
...
On occasions where the Recall-value is greater than 0.00, but still unexpectedly low, your trained algorithm application seems not to perform optimally when recognizing your annotated instances.
...
First, you need to check, if the annotations on your validation images are correct and complete (i.e. whether all target instances have been annotated). If annotations are not correct and complete, then you may have omitted annotations in your training images. This can be the reason for the low Recall-value, as the algorithm application will also mimic your annotation behavior and omit instances.
Further, you can add more annotated regions with the label of your interest to the training set to improve your performance. You will get the optimal improvements by adding images or ROI(s) containing instances with a similar appearance to the validation images that have not been correctly classified by the algorithmtrained model.
If annotations are correct and complete, then you can improve your algorithm by adding new images or ROI(s) containing annotations to the training set. You will get the optimal improvements by adding images or ROI(s) containing instances with a similar appearance to the regions in the validation images that have not been correctly classified by the algorithmtrained model.
📑 Case 4 - An image or an ROI contains no manual annotations, but there is a prediction (Precision equals 0.00 or is unexpectedly low).
...
This is a false-positive prediction made by your trained algorithmapplication.
On occasions where the Precision-value is greater than 0.00, but still unexpectedly low, your trained algorithm model seems to predict instances in your validation images that have not been annotated. This can either be due to the fact that the algorithm application has made false-positive predictions or that some annotations in your validation images do not include all target instances.
...
Verify if there are really no instances of the target labels present in the image(s) or ROI(s). Try to add images or ROI(s) that have a similar appearance to the ones containing false-positive predictions.
Have a look at the annotations in your validation images in cases where the algorithm app has performed a segmentation task and check whether the annotations are complete. If annotations are correct and complete, then you can improve your algorithm trained model by adding new images or ROI(s) without any instances to the training set.
You will get the optimal improvements by adding images or ROI(s) containing instances with a similar appearance as the areas that have been detected by the algorithm in the validation images.
...
Having successfully alleviated all frustrating false prediction issues, you can now use the potential of your trained algorithms applications to full advantage!
Share this article with a colleague, if it has helped you!
...
If you still have questions regarding your algorithm application training, feel free to send us an email at support@ikosa.ai. Copy-paste your training ID in the subject line of your email.
...