DeDoDe doesn't produce absolute confidence?

[nnop]

Hi, thanks for the great work.

I found that DeDoDe calculates the Softmax confidence over the entire image and the max resulting confidence is very low, e.g. 0.00095387973 in my test.

DeDoDe/DeDoDe/detectors/dedode_detector.py

Line 47 in 0928deb

keypoint_p = keypoint_logits.reshape(B, K*H*W).softmax(dim=-1).reshape(B, K, H*W).sum(dim=1)

So how can I set an absolute confidence threshold (for example: 0.1) to filter out non salient area?

[Parskatt]

I don't recommend doing that. The filtering is done by topk. If you want to set a threshold, perhaps you can set it based on the max over the image, e.g.., t= 0.01 * maxprob

[nnop]

Thanks for your suggestion. I think that's practial.

Another question about the params.
Why set use_nms=False in detect(). Wouldn't nms help?