minaghadimiatigh / hyperbolicimagesegmentation Goto Github PK
View Code? Open in Web Editor NEWHyperbolic Image Segmentation, CVPR 2022
Home Page: https://minaghadimi.github.io/papers/HIS/index.html
Hyperbolic Image Segmentation, CVPR 2022
Home Page: https://minaghadimi.github.io/papers/HIS/index.html
Thanks for open-sourcing such as a wonderful work, could you please kindly help answer these questions?
The function “hyp_mlr” in hesp/utils/layers.py seems like contradictory to Eq. 7 in your paper Hyperbolic Image Segmentation. It looks like you did not divide ||wy|| when computing the input to sinh-1, also you did not multiply \lambda^{c}_{p_y}.
Eq. 12 in your paper said that you multiply conditional probabilities along the ancestor to current descendant, however in function “get_joints” in hesp/embedding_space/abstract_embedding_space.py, It seems like you add them instead of multiplying, then in “decide” function you choose the maximum added conditionals as the prediction.
Hi - Thank you for the great piece of work!
I was wondering if you were planning on posting the code used for plotting the classes gyroplane on the Poincare ball (i.e. Fig. 1) ? I tried to find more information in the supplementary material as for how these were plotted but in vain.
Thank you!
Darius
How do I get the Hyperbolic Uncertainty map of a picture?
Thank you for sharing the code~
Will trained models also be shared later?
Hi, thanks for the interesting paper.
I think the following part is the code for hyperbolic logit (paper equation(7)), and it seems that there is no
Hi, thanks for the interesting paper! I would be curious to test your implementation and ideas on some custom datasets. However, I noticed that you have not added a license to the code release. Would you consider adding a license?
Hi! Thanks for sharing the code!
I tried to reproduce this work but had some trouble finding 'coco_train.record' and 'coco_val.record'.
Will these files be shared? Or shall I download them from elsewhere?
Thank you!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.