Patchcore: the value of k in nearest neighbor search

[ghost]

Thanks to your efforts,
I've noticed in the code of patchcore,
doing k nearest neighbor search,

ind_knn_ad/indad/models.py

Line 286 in 5510f0f

_, nn_idx = torch.topk(w_dist, k=self.n_reweight, largest=False) # pt.2

the value of k is set to 3,
can I ask how to determine the value of k?
can I set k=1?

[rvorias]

Thanks for your question. I believe I got 3 from the original paper.
The best k depends on your dataset and your validation performance.
You can indeed set k=1.

[ghost]

Thanks to your explanation,
I'm confused because two other implementations
anomalib and hcw-00
they both set the value of k to 9.

Fig.4 top in the paper, I'm not sure the 'neighborhood size' here is refer to the local neighborhood aggregation part (the Avgpool operation) or the k neighbor search operation...

[rvorias]

I've always interpreted the local neighborhood aggregation part as avgpool part.