How to apply word2vec on images?

Question

I have been studying word2vec model by Google. I was able to generate vectors for text word corpus for maximum 300 dimensions. It is a very impressive tool and accuracy goes much further, on big data.

I am curious, is there any way to use word2vec to generate vectors on grayscale images. I am sure the approach is same, you generate vectors based on pixel intensity and then compute a cosine similarity.

I am trying to do build a model to compute similarity distance on grayscale images. Any library is capable of doing this besides word2vec or glove that works on text?

Answer 1

I agree with you that word2vec is very impressive tool, but this model is trained by predicting the next word in some article or news. All in all, I think that using word2vec on image does not make sense.

You can use skimage to do some image measure. e.g skimage-measure