Open ducha-aiki opened 11 months ago
Hi,
I am wondering, can we just use mutual nearest neighbor matching for speed at inference time? Dual softmax normalizes the scores, but doesn't change the actual neighbors (matches).
We have a confidence threshold for the matches based on the ds scores. If you remove that youll get more outliers.
Otherwise yes, I see no major issue.
Hi,
I am wondering, can we just use mutual nearest neighbor matching for speed at inference time? Dual softmax normalizes the scores, but doesn't change the actual neighbors (matches).