Comments (6)
@ducha-aiki Thank you for your reply! I think i have understood your idea. Affnet makes the detector more reliable and thus helps improve the final result. If retrain the hardnet, we still focus on the descriptor training and will lose the sense of your design of affnet.
from affnet.
Original comes from https://github.com/DagnyT/hardnet
It needs not to retrain, because affnet makes its life easier. If one retrains hardnet afterwards, I expect it becomes less robust. Moreover, it is an idea of modular local features - to be detector, shape and descriptor to be upgradable w/o retain.
from affnet.
By the way, how many features do you choose of the hessian detector in testing oxford? i find some samples are not able to extract 3000, the number in your matching example.
from affnet.
from affnet.
@ym547559398 I haven`t used fixed number, instead used Hessian threshold as below to be fully compatible with previous experiments:
https://dspace.cvut.cz/bitstream/handle/10467/9548/2009-Efficient-representation-of-local-geometry-for-large-scale-object-retrieval.pdf
https://github.com/perdoch/hesaff/blob/master/pyramid.h#L37
from affnet.
@ducha-aiki I have tested your released model on roxford dataset, but the final result is not good as follows:
roxford5k: mAP E: 67.17, M: 53.37, H: 30.37
roxford5k: mP@k[ 1 5 10] E: [95.59 72.06 55.88], M: [97.14 81.43 62.86 ], H:[78.57 31.43 14.29]
My scheme is:
- Use hessian detector and affnet to extract 3000 features and hardnet++ to extract descriptors which is 3000*128.
- Use Ransac to find good matches between each query and reference and use the sum of matchMask as score.
- Use revisitop to evaluate the result.
Can you give me some suggestions?
from affnet.
Related Issues (20)
- nmsed_resp HOT 6
- Exact_Pacthes HOT 8
- Comparison to vl_covdet() HOT 1
- AffNetFastFullAff architecture missing HOT 2
- Is the experiments of Oxford Dataset retrieval task using BoW available? HOT 3
- Question about evaluating the model on roxford dataset HOT 11
- Aligning 2 images using affnet HOT 8
- why the validation of handcrafted Baumberg Iteration runs without orientation HOT 2
- Some suggestions for the people to visit HOT 3
- About AffNet training(Fig.5) HOT 2
- About train_OriNet_test_on_graffity.py HOT 1
- RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation
- About the version of the python and pytorch HOT 2
- How to get feature's scale and orientation HOT 7
- get keypoints HOT 1
- RuntimeError: [enforce fail at CPUAllocator.cpp:47] HOT 4
- How to get
- How to get the A matrixs which satisfies the Geometric constraints condition EP=-AEP? HOT 7
- About the AFFNET HOT 2
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 affnet.