Comments (3)
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.
Related Issues (20)
- hfnet inference with C++ HOT 1
- 'Config' error during evaluation lfnet for hpatches. HOT 1
- Hllo HOT 1
- About disstillation in the global descriptor HOT 3
- About the training process
- Training Dataset HOT 1
- NetVLAD Descriptors for Training HOT 1
- why triangulate the aachen 3D model according to matches instead of using 3d points provided? HOT 2
- Training with TUM HOT 6
- error during evaluation aachen
- Question about databases contents
- RobotCar Seasons evaluation issues HOT 4
- About train and evaluation of HFNet.
- Extremely large size npz files during SuperPoint export_predictions
- undefined variables output_types, output_shape HOT 1
- Hello professor, I met some problems while processing local evaluation.
- Experiences for adjusting the weights in the loss when retraining HFNET with 128D local descriptor
- Is python 3.6 mandatory?
- Question about Intra-Normalization
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from hfnet.