A strange gap between how's global feature similarity and how's local feature similarity with ASMK

[aruba01]

In my understanding, the paper contains two kinds of image-level similarity, one is measured by the global feature, another is measured by the local feature with ASMK.

In some research, similarity measured by global feature is enough. I guess that the reason you choose local feature similarity is the ASMK similarity can improve the performance of global feature. So I tested how much performance can be improved. The results is following.

HOW INFO: Evaluated roxford5k: mAP E: 65.56, M: 49.66, H: 24.41

HOW INFO: Evaluated rparis6k: mAP E: 80.64, M: 63.07, H: 36.0

The improvement is expected, but the performance of the global feature is too poor. I thought the mAP of roxford5k(M) and rparis6k(M) could be 60-70. This is a strange phenomenon that bad global feature can generate good local feature. I want to know more about it. Does it mean ASMK is a wonderful method?