About data preprocess and data augmentation

[shuhao]

I want to know more detail about data prepocessing especially cropping strategy.

[Yilun Chen]

You can find the summary of our data preprocessing and post-processing strategies in our paper.

[shuhao]

Do you use bounding box of ground truth directly without no disturbance during training?

[Yilun Chen]

Multi-scale training is applied

[shuhao]

Yes, I see that in dataset.py. I wonder know why you do not use results of the detector and calculate IOU as the prediction of instance.

[Yilun Chen]

I didn’t get it. If you mean we directly train using the detection boxes, I think its performance works like multi scale training and maybe random shifts of the boxes. I think random shifts of boxes can help, which we didn’t try it. As well if you want to exploit the specific detector.