Comments (4)
Yes your comment is spot on, actually this one reason we use some scheduling on alpha (the other reason is that it simplify the hyper-parameters search).
The predictions being only zeros are a problem known for this kind of method (as mentioned in the rebuttal, the second version of the paper, and perhaps a few Github issues but I cannot find them right now), and so that is why we do not use the loss on this own on those problems.
A few things however to consider:
- What actually matters is not necessarily the loss value, but the gradients it produces (hence mean and sum are pretty much the same for reduction)
- Those problems are less present in the multi-class problem, where the other classes are not hard-negatives of the first class.
I invite you to watch the talk I gave last July, I feel a lot of what I said there is relevant to your questions: https://www.youtube.com/watch?v=_z6gmFlD_qE
Let me know is that wasn't clear enough, I will make a more detailed reply.
from boundary-loss.
Just a follow up question: Why do you propose using a signed distance map instead of an unsigned distance map? Did you observe a significant difference in your experiments between the two formats?
If you look at the proof of Equation (4) that I posted in #9 (comment) , you will see where the negative sign comes from and how it helps to simplify the equation.
Also, if you look at the boundary loss as purely a distance based penalty, you will notice that the gradient will be negative inside the object ; pushing up the logits and probabilities for target class during the gradient descent. Opposingly, the background pixels have a positive gradient, pushing the predicted probabilities down during SGD.
If the distance map wasn't signed, it would push the predicted probabilities down for all pixels, be it foreground or background.
from boundary-loss.
Thanks for replying!
Just a follow up question: Why do you propose using a signed distance map instead of an unsigned distance map? Did you observe a significant difference in your experiments between the two formats? I would think that, for a given image, the optimal segmentations for GDL and signed distance map are different, whereas the optimal segmentations for GDL and unsigned distance maps are the same.
from boundary-loss.
Thanks!
from boundary-loss.
Related Issues (20)
- Does einsum really make the code easier to understand HOT 2
- ISLES 2018 HOT 1
- Heterogeneous resolution yields non-zero boundary. HOT 5
- InvalidArgumentError: required broadcastable shapes at loc(unknown) [Op:Mul] HOT 2
- Can this loss be used for multi-label classification? HOT 4
- Create dist_map for image segmentation mask as label. HOT 2
- Is multiplication by negmask in one_hot2dist() irrelevant? HOT 2
- Question about the optional argument resolution in the dist_map_transform function HOT 1
- About the calculation of dist_map HOT 5
- how to use with sigmoid as activation function when meeting binary classification segmentation task HOT 3
- how to adjust the lambda parameter HOT 5
- How to use HausdorffLoss? HOT 1
- How to use HausdorffLoss? HOT 1
- How to one-hot encode a multi-class dataset and how to use Boundary Loss on B x N x W x H logits? HOT 2
- Only using boundary loss leads to non convergence HOT 1
- Failure of matching datasets of WMH HOT 1
- Is it possible to train the Boundary Loss code on a GPU? HOT 1
- Whether this loss function can be applied to the partition of a hollow region, that is, a region with two boundaries HOT 2
- License Request
- zero question
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 boundary-loss.