Suppose we have a prototype CBIR pipeline which allows us to index global image descriptors using a linear indexing . We measured a mean average precision (mAP) of for our system, using a test set T1 . We now plan to use another indexing technique suitable for a larger scale: we will use some approximate nearest neighbor technique (like hierarchical k-means or LSH). What should be the expected , likely values for the mAP of our system with the new indexing approach , when using the same test set T1 ?

Question

Suppose we have a  prototype CBIR pipeline  which allows us to index global image descriptors using a  linear indexing . We measured a mean average precision (mAP) of    for our system, using  a  test set T1 . We now plan to use  another indexing technique  suitable for a  larger scale:  we will use some  approximate nearest neighbor  technique (like hierarchical k-means or LSH). What should be the  expected , likely values for the mAP  of our system with the  new indexing approach , when using the  same test set T1 ?

Answer

The new mAP  should  be  greater than    .

Answer

The new mAP  should  be  lower than    .

Answer

The new mAP  should  be  exactly equal  to   .

Crowdly

Suppose we have a prototype CBIR pipeline which allows us to index global imag...

Want instant access to all verified answers on moodle.epita.fr?