Setting the config correct for numerous, small objects

[s-weissbach]

Hello,

I need assistance in configuring the settings for a segmentation task that involves detecting multiple smaller objects. I've already modified the DETECTIONS_PER_IMAGE: 100 flag for inference, but I'm curious if there are specific parameters that can be adjusted during training to enable more detections or to fine-tune the expected size of the detected objects.

Any guidance on this matter would be greatly appreciated. Thank you!