cvat | Powerful and efficient Computer Vision Annotation Tool | Data Labeling library

I have a set of frames in which different animals are visible. I have annotated them using CVAT's polygon feature. Now, all I need to do is cropping the annotation part and extracting the features as a CSV file.

I can extract the features using VGG16 in MATLAB using a code like below:

Is it mandatory to annotate images using polygon shapes for mask rcnn? I read the https://github.com/matterport/Mask_RCNN and the research paper as well. It seems that matterport's implementation can take bounding box as well as polygon as annotations. Although I am not certain. So should I consider bounding box annotation for my dataset? or polygon annotation?

Currently I have annotated some images using bounding box on Intel's CVAT.

I have trained a YoloV4 CNN. It's pretty good already. I want more images as training data but there is no point of manually annotate most of the stuff because CNN can do it for me. I could review and re-correct if there are any issues. Is there a image annotation tool/service that can do that? I'm currently using Supervisely. I also tried CVAT and VoTT Couldn't find such feature.

This is my first foray into the world of object recognition. I have successfully trained a model on yolo with images that I have found on Google and annotated myself in CVAT.

My questions are as follows.

a) How do I train the model to ignore some special variant that I am specifically NOT interested in detecting? Say I am getting false positives because something looks similar to one of my objects, and I want to train so that these are not detected. Does it simply work to include images that contain the unwanted object into the training set, but don't annotate the unwanted object?

b) If so, am I right in assuming that if I train on annotated images that have somehow missed occasional instances of desired objects, is that effectively telling the training engine that I'm not interested in that object? In other words, is it therefore BAD if images don't have every single instance of desired objects annotated?

c) If I happen to include an image in my training set with an empty annotation file, and there are desired objects in that image, that effectively disincentivizes the training engine to find those in future?

Thanks for any thoughts.

I am able to build and run cvat tool. But when I trying to create a superuser then it is giving me below error.

ImportError: No module named 'gitdb.utils.compat'

I am running below command for creating a superuser.

docker exec -it cvat bash -ic 'python3 ~/manage.py createsuperuser'

Does anyone have any idea or suggestion for the above problem?