is the global descriptor of hfnet better than netvlad? about hfnet HOT 3 CLOSED

This is an interesting question. If you look at the ablation study (table 4 in the paper), you can notice that:

• NV+HF-Net performs better than NV+SP, so the distillation improves the performance of the local features.
• NV+HF-Net performs better than HF-Net, so the distillation yields less robust global descriptors.

We did not aim at improving the performance on both tasks, but I believe that it is possible with better losses and careful balancing.

from hfnet.

This is an interesting question. If you look at the ablation study (table 4 in the paper), you can notice that:

* NV+HF-Net performs better than NV+SP, so the distillation improves the performance of the local features.

* NV+HF-Net performs better than HF-Net, so the distillation yields less robust global descriptors.

We did not aim at improving the performance on both tasks, but I believe that it is possible with better losses and careful balancing.

ok. In my case I only want the global retrieval part since the localization is done by lidar. I want to improve the global retrieval performance for datasets with lots of dynamic objects. Have you tried training the model using only global supervision from NV without local head? What if I have posed images so that direct supervision, e.g. via Siamse net architecture, is possible?

from hfnet.

There is a whole body of literature on learning image retrieval from pose labels only, e.g. the work of Thoma et al.. This is out of the scope of this repository.

from hfnet.