Open dmarx opened 11 months ago
alternatively, could solve against the entire stack of names with a sparsity-enducing regularization term, like a strong L1 loss or a sparse VAE or whatever
shit, i might even be able to just softmax the similarity scores and use that as the neighbor weights, or maybe set some threshold above which a vector gets included in the optimization
grab the K nearest neighbors of some input image(s), solve for linear combination (weighted sum) approximation in the k-neighbors basis.
if multiple images provided, get k-neighbors for each. could optionally even specify weights for each provided image in computing the loss for solving the basis