keras-cv
keras-cv copied to clipboard
keras-team
Add ArcFace loss.
System information.
TensorFlow version (you are using): 2.8 Are you willing to contribute it (Yes/No) : No (but willing to provide starter if required.)
Describe the feature and the current behavior/state.
ArcFace, or Additive Angular Margin Loss, is a loss function used mainly in face recognition tasks. It is used to obtain highly discriminative features. This loss function can be used in both vision task and nlp task. So, I think its general for .keras_cv and keras_nlp
Paper: https://arxiv.org/pdf/1801.07698.pdf, TL,DR, https://paperswithcode.com/method/arcface Citation: 2939 (current)
Will this change the current api? How?
tf.keras.losses.SparseArcFace
tf.keras.losses.CategoricalArcFace
Who will benefit from this feature?
keras practitioners.
- Briefly describe your candidate solution(if contributing):
- https://github.com/4uiiurz1/keras-arcface
ArcFace, or Additive Angular Margin Loss, is a loss function used mainly in face recognition tasks
What are some NLP use cases? It seems like it might be a good fit for KerasCV specifically.
Sorry I miswrote, it should be only CV task. Could you please move this issue to KerasCV?
Hey, @LukeWood @sayakpaul I think this would be a great feature addition to KerasCV. It's especially popular in Kaggle competitions for reference.
Please assign it to me.
I concur. Especially for retrieval tasks, ArcFace loss is greatly beneficial.
interesting, can this be used with the existing models we have? i.e. if we add this will we have the tools we need to support facial recognition?
So theoretically, we include this, and use this loss to create a facial recognition tutorial with the other existing components?
Shoul be the case. We have a tutorial on few-shot learning and we coul definitely take some components from that too.
Shoul be the case. We have a tutorial on few-shot learning and we coul definitely take some components from that too.
ok, sounds good. Then I think this is a great component. Especially if we can include a tutorial on facial recognition.
When we do include this I do think it’s important to have a tutorial showing off how to use it, so let’s keep that in mind! Doesn’t have to be anything crazy, just some basics!
This loss is compatible with existing models.
I can take this up. Will start working on it soon. Also the idea of tutorial is great for this loss.
It looks like this fell through the cracks @alexandrekj. @yashchks87 or @alexandrekj, are either of you interested in working on this?
