Add Barlow Twins loss for representation learning #7530
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Lucas Robinet <robinet.lucas@iuct-oncopole.fr>
Lucas-rbnt
force-pushed
the
barlow-twins
branch
from
1371b0d to
393d415
Compare
ericspod
reviewed
Mar 11, 2024
ericspod
reviewed
Mar 11, 2024
ericspod
reviewed
Mar 11, 2024
Co-authored-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com> Signed-off-by: Lucas Robinet <67736918+Lucas-rbnt@users.noreply.github.com>
Co-authored-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com> Signed-off-by: Lucas Robinet <67736918+Lucas-rbnt@users.noreply.github.com>
…s aim and use cases Signed-off-by: Lucas Robinet <robinet.lucas@iuct-oncopole.fr>
ericspod
reviewed
Mar 11, 2024
Co-authored-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com> Signed-off-by: Lucas Robinet <67736918+Lucas-rbnt@users.noreply.github.com>
KumoLiu
approved these changes
Mar 18, 2024
Co-authored-by: YunLiu <55491388+KumoLiu@users.noreply.github.com> Signed-off-by: Lucas Robinet <67736918+Lucas-rbnt@users.noreply.github.com>
for more information, see https://pre-commit.ci
Signed-off-by: Lucas Robinet <robinet.lucas@iuct-oncopole.fr>
|
/build |
1 similar comment
|
/build |
juampatronics
pushed a commit
to juampatronics/MONAI
that referenced
this pull request
Mar 25, 2024
### Description Addition of the BarlowTwinsLoss class. This cost function is introduced in the http://proceedings.mlr.press/v139/zbontar21a/zbontar21a.pdf paper with the aim of disentangling the representations learned on two views of the same sample, making it a powerful tool for multimodal and unsupervised learning. This cost function is similar to the InfoNCE Loss function already implemented in MONAI (https://docs.monai.io/en/latest/_modules/monai/losses/contrastive.html#ContrastiveLoss). However, it differs in several respects: there is no l2-normalisation, but rather a z-normalisation. In addition, rather than working between pairs of embeddings, Barlow Twins seeks to decorrelate the components of the representations. ```math \mathcal{L}_{BT} := \sum_i (1 - \mathcal{C}_{ii})^2 + \lambda \sum_i \sum_{i\neq j} \mathcal{C}_{ij}^2 ``` with $\lambda$ a positive hyperparameters and $\mathcal{C}$ the cross-correlation matrix ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. --------- Signed-off-by: Lucas Robinet <robinet.lucas@iuct-oncopole.fr> Signed-off-by: Lucas Robinet <67736918+Lucas-rbnt@users.noreply.github.com> Co-authored-by: Lucas Robinet <robinet.lucas@iuct-oncopole.fr> Co-authored-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com> Co-authored-by: YunLiu <55491388+KumoLiu@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Signed-off-by: Juan Pablo de la Cruz Gutiérrez <juampatronics@gmail.com>
Yu0610
pushed a commit
to Yu0610/MONAI
that referenced
this pull request
Apr 11, 2024
### Description Addition of the BarlowTwinsLoss class. This cost function is introduced in the http://proceedings.mlr.press/v139/zbontar21a/zbontar21a.pdf paper with the aim of disentangling the representations learned on two views of the same sample, making it a powerful tool for multimodal and unsupervised learning. This cost function is similar to the InfoNCE Loss function already implemented in MONAI (https://docs.monai.io/en/latest/_modules/monai/losses/contrastive.html#ContrastiveLoss). However, it differs in several respects: there is no l2-normalisation, but rather a z-normalisation. In addition, rather than working between pairs of embeddings, Barlow Twins seeks to decorrelate the components of the representations. ```math \mathcal{L}_{BT} := \sum_i (1 - \mathcal{C}_{ii})^2 + \lambda \sum_i \sum_{i\neq j} \mathcal{C}_{ij}^2 ``` with $\lambda$ a positive hyperparameters and $\mathcal{C}$ the cross-correlation matrix ### Types of changes <!--- Put an `x` in all the boxes that apply, and remove the not applicable items --> - [x] Non-breaking change (fix or new feature that would not break existing functionality). - [ ] Breaking change (fix or new feature that would cause existing functionality to change). - [x] New tests added to cover the changes. - [x] Integration tests passed locally by running `./runtests.sh -f -u --net --coverage`. - [x] Quick tests passed locally by running `./runtests.sh --quick --unittests --disttests`. - [x] In-line docstrings updated. - [x] Documentation updated, tested `make html` command in the `docs/` folder. --------- Signed-off-by: Lucas Robinet <robinet.lucas@iuct-oncopole.fr> Signed-off-by: Lucas Robinet <67736918+Lucas-rbnt@users.noreply.github.com> Co-authored-by: Lucas Robinet <robinet.lucas@iuct-oncopole.fr> Co-authored-by: Eric Kerfoot <17726042+ericspod@users.noreply.github.com> Co-authored-by: YunLiu <55491388+KumoLiu@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Signed-off-by: Yu0610 <612410030@alum.ccu.edu.tw>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Addition of the BarlowTwinsLoss class. This cost function is introduced in the http://proceedings.mlr.press/v139/zbontar21a/zbontar21a.pdf paper with the aim of disentangling the representations learned on two views of the same sample, making it a powerful tool for multimodal and unsupervised learning.
This cost function is similar to the InfoNCE Loss function already implemented in MONAI (https://docs.monai.io/en/latest/_modules/monai/losses/contrastive.html#ContrastiveLoss). However, it differs in several respects: there is no l2-normalisation, but rather a z-normalisation. In addition, rather than working between pairs of embeddings, Barlow Twins seeks to decorrelate the components of the representations.
with$\lambda$ a positive hyperparameters and $\mathcal{C}$ the cross-correlation matrix
Types of changes
./runtests.sh -f -u --net --coverage../runtests.sh --quick --unittests --disttests.make htmlcommand in thedocs/folder.