I am currently working on an object detection project in which I amtrying to detect very small objects 50x50 object in a 2k image.

EfficientDet produced a very low result if I just put the raw annotations and start training.

So my question is: Is there any pre process technique, apart from augmentation, that would help improving the model?

enter image description here


I'm struggling with a similar problem myself.

Could you please provide details about:

  • What version of efficientDet you are using
  • What preprocessing you are currently using on the images

One solution is to divide the images into smaller images. At this years Nvidia GTC conference, ConservationAI did a talk where they mentioned that they split up 8k images to a desired resolution. The talk can be found on the GTC website. The relevant part is at about 30:42


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.