Fishr is a learning scheme to enforce domain invariance in the space of the gradients of the loss function: specifically, it introduces a regularization term that matches the domain-level variances of gradients across training domains. Critically, the strategy exhibits close relations with the Fisher Information and the Hessian of the loss. Forcing domain-level gradient covariances to be similar during the learning procedure eventually aligns the domain-level loss landscapes locally around the final weights.
Source: Fishr: Invariant Gradient Variances for Out-of-Distribution GeneralizationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Domain Generalization | 2 | 50.00% |
Autonomous Vehicles | 1 | 25.00% |
Federated Learning | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |