search

yxgeee / OpenIBL

[ECCV-2020 (spotlight)] Self-supervising Fine-grained Region Similarities for Large-scale Image Localization. 🌏 PyTorch open-source toolbox for image-based localization (place recognition).
https://yxgeee.github.io/projects/sfrs
MIT License
271 stars 41 forks source link

Question on tab.3 of the paper #19

Closed XiSHEN0220 closed 3 years ago

XiSHEN0220 commented 3 years ago

Hi, thanks for sharing your nice work!!!

Looking into the paper, I realise that it also includes comparaisons on Oxford and Paris.
As I know, there are other approaches report better performances on these benchmarks, such as : Fine-tuning CNN Image Retrieval with No Human Annotation. They report 87.8 in terms of mAP on Oxford.

I am wondering whether there are particular reasons that these two lines of research are not comparable.

Thanks in advance,

Best

yxgeee commented 3 years ago

We did not train on these retrieval datasets (e.g. Oxford, Paris). We just show the generalization ability of our model by directly testing it. The same protocol was used by NetVLAD and SARE.

The one you mentioned, as well as the other works that focused on image retrieval, trained and tested their models on the same retrieval datasets. Thus they are not comparable with our methods.

XiSHEN0220 commented 3 years ago

Thanks for your reply. :) I close the issue.