1

I'm having problems in finding the best network and configuration to detect small-scale objects. Since now I got very Los mAPs on small objects (i am trying to detect traffic Signs using mapillary dataset)

I have tried using Faster R-CNN 101 (resizing the input to 1024) and the SSD 101 with FPN (resizing the input to 1024). I did not find a pre-trained model of faster R-CNN with FPN so i could not try that.

What do you think would be the best network and confuguration to detect small objects?

Thank you.

Improve this question
2
  • Are you detecting only small objects or small and large objects? Do you care about speed of the detector (do you need real-time detections) or only about accuracy? Commented Oct 20, 2020 at 9:19
  • I am detecting both small and large objects (the original resolutions of the images are pretty high). In my case speed is not so important, I would prefer higher accuracy. Commented Oct 20, 2020 at 17:05

2 Answers 2

Reset to default
1

The models you mentioned are models that are built for speed. With small object detection, you often care more about accuracy of the model. So you should probably use bigger models that sacrifice speed for accuracy (mAP). If you want to use tensorflow 2, here is an overview of the available models. Also, for small object detection you should keep high resolution, as you said. You could also maybe crop images into multiple crops instead, to detect on portions of images.

So I disagree with @Akash Desai about SSD, but I also think that detectron2 is more up to date to state of the art models for better performance. So if you don't care about the framework, maybe switch to detectron2.

Improve this answer
Sign up to request clarification or add additional context in comments.

Comments

0

SSD is best for detecting small as well as large target ,because it will try to do prediction on each and every feature map.

you resized images to 1024 ??? it this case model will take more time to train on dataset, so keep the size of images small like 460*460.

also you can try with detectron2 ,its faster & simpler than tensorflow.

https://colab.research.google.com/github/Tony607/detectron2_instance_segmentation_demo/blob/master/Detectron2_custom_coco_data_segmentation.ipynb
Improve this answer

Comments

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.