Specify negatives in PyTorch-Object Detection

Hey folks,

I have a decent setup going using Dusty’s Jetson utils and have trained a great custom network on the pytorch object detection however while I am aware that any space outside of the label is labeled as background and counted as negatives in the network I am wondering if there is a way of feeding just negatives to update the model?

The reason being I have new environments I want it to detect in, but there is so much in these environments it has never seen before, so it is producing new false positives. I would like to be able to feed these new environments in without having to spend hours and hours doing vfx to composite my object in the footage and synthesize new data sets.

Any ideas?


Hi @TP2049, I haven’t tried this before, but have you tried adding these ‘negative’ images to your dataset without any annotated objects in their XML files?