A curious phenomenon in image retrieval

[aruba01]

I do image retrieval task with --use_geometric_verification on the code perform_retrieval.py in delg folder. To compare different local feature, I tried to replace the local feature of delg with Superpoint. But the performance is lower than the baseline (do global retrieval only). as far as I am concerned, geometry verification is a commom method to improve the performance.

I wanna know that is this phenomenon normal? Does it means geometry verification can't improve the performance definitely?

the result of Superpoint is shown below:

hard
mAP=45.17
mP@k[ 1 5 10] [87.14 71.43 60.29]
mR@k[ 1 5 10] [19.29 29.39 36.42]
hard_after_gv
mAP=41.04
mP@k[ 1 5 10] [84.29 68.57 56.57]
mR@k[ 1 5 10] [19.01 27.18 31.21]
medium
mAP=69.75
mP@k[ 1 5 10] [95.71 92. 86.86]
mR@k[ 1 5 10] [10.17 25.94 33.84]
medium_after_gv
mAP=67.29
mP@k[ 1 5 10] [95.71 91.43 86.14]
mR@k[ 1 5 10] [10.19 25.67 33.6 ]

[laxmareddyp]

Hi @aruba01,

It looks like you haven't used a template to create this issue. Please resubmit your issue using a template from here. We ask users to use the template because it reduces overall time to resolve a new issue by avoiding extra communication to get to the root of the issue. We will close this issue in lieu of the new one you will create from the template. Thank you for your cooperation.

[aruba01]

Hi @aruba01,

It looks like you haven't used a template to create this issue. Please resubmit your issue using a template from here. We ask users to use the template because it reduces overall time to resolve a new issue by avoiding extra communication to get to the root of the issue. We will close this issue in lieu of the new one you will create from the template. Thank you for your cooperation.

I submit the issue in branch tensorflow\models, so i use the template from https://github.com/tensorflow/models/issues/new/choose. The template you mentioned seems used in tensorflow\tensorflow.

[laxmareddyp]

Hi @aruba01 ,

Sorry It was my mistake , default template pointing out to tensorflow\tensorflow..
we will check the issue.

Thanks.