Is the experiments of Oxford Dataset retrieval task using BoW available? about affnet HOT 3 CLOSED

Hi,

Things regarding feature extraction are here:

https://github.com/ducha-aiki/mods-light-zmq#if-you-need-to-extract-and-save-features-from-directory-with-images

These gives you features and geometry. Regarding BoW itself, unfortunately, it is lab`s proprietary matlab code.

You could try this ASMK from here, but it is not the same

http://cmp.felk.cvut.cz/~toliageo/soft.html

from affnet.

When clustering with kmneas methods into 1M vocabulary, it takes a really long time and I do not see the end.
Any advises?

from affnet.

1)Use faiss https://github.com/facebookresearch/faiss
or 2)use approximate KNN method like kd-tree for calculating nearest cluster center.

from affnet.