sahi

See the url in my comment (search for the term rfdetr-2xlarge). 2XL does indeed go up to 800x800 and has PML1.0 license instead of apache 2.0. Rescaling is fine for some purposes but but not for all. For many domain-specific (often less common and odd dimensioned) objects, downscaling will severely reduce recall. There is a reason that Roboflow slaps a license that is not open source on those specific architectures. In some cases tiled inferencing (for example with https://github.com/obss/sahi ) might do the job.

Good idea. I haven’t looked too closely yet at the “hard” datasets. We originally considered “fixing” the labels on these datasets by hand, but ultimately decided that label error is one of the challenges “real world” datasets have that models should work to become more robust against. There is some selection bias in that we did make sure that the datasets we chose passed the eye test (in other words, it looked like the user spent a considerable amount of time annotating & a sample of the images looked like they labeled some object of interest). For aerial images in particular my guess would be that these models suffer from the “small object problem”[1] where the subjects are tiny compared to the size of the image. Trying a sliding window based approach like SAHI[2] on them would probably produce much better results (at the expense of muc

That's the main approach I've encountered. Slice, inference, filter duplicates from the results. https://github.com/obss/sahi