Mistake in computing average precision about cnn-for-image-retrieval HOT 8 OPEN

Yeah, I saw your blog on MAP computation. It's right and clear. I meant your implementation (computer_MAP.m) maybe have an error in computing average precision for each retrieval. Just as,
queryClassNum = double(classesAndNum{1, 2}(row1,1));
ap(i,1) = sum(precision)/queryClassNum;
The denominator in above formula should be a variable depending on the retrieval results rather than a constant. So I slightly revised it as,
retrievalSamples=sum(precision~=0);
ap(i,1) = sum(precision)/retrievalSamples;
and it seems return me a right results for my problem. Thanks.

from cnn-for-image-retrieval.

@kylinXu I followed this mAP computation to get the mAP score. The mAP computation shows in the post is very clear. I hope the figure in the post helps you to understand the mAP computation.

from cnn-for-image-retrieval.

It's true, thank you for point out the potential risk. I'll check out it today.

from cnn-for-image-retrieval.

from cnn-for-image-retrieval.

I just want to know the result when the pictures in Date base is very huge, about 10 million. Really hope receive your answer.

from cnn-for-image-retrieval.

It depends on your task, instance retrieval or similar retrieval. For similar retrieval (category retrieval), it's really OK.For instance retrieval, you might be interested in cnn-cbir-benchmark. There are some references which might be useful for you awesome-cbir-papers.

from cnn-for-image-retrieval.

Thanks for your answer, buy the way, how many pictures should I prepared for fine-tuning, I'm worried about that, because I can't labeled so many pictures .

from cnn-for-image-retrieval.

If you don't want to labeled so many pictures, you can choose method based on local feature. flickrdemo.videntifier.com is a demo based on SIFT feature. The performance is really promising.

from cnn-for-image-retrieval.