Gradient matching for domain generalization
Machine learning systems typically assume that the distributions of training and test sets match closely. However, a critical requirement of such systems in the real world is their ability to generalize to unseen domains. Here, we propose an inter-domain gradient matching objective that targets doma...
Main Authors: | Shi, Y, Seely, J, Torr, PHS, Siddharth, N, Hannun, A, Usunier, N, Synnaeve, G |
---|---|
Format: | Conference item |
Language: | English |
Published: |
OpenReview
2022
|
Similar Items
-
Value propagation networks
by: Nardelli, N, et al.
Published: (2019) -
FedSR: a simple and effective domain generalization method for federated learning
by: Nguyen, AT, et al.
Published: (2023) -
Domain-invariant stereo matching networks
by: Zhang, F, et al.
Published: (2020) -
Growing action spaces
by: Farquhar, G, et al.
Published: (2020) -
Adversarial masking for self-supervised learning
by: Shi, Y, et al.
Published: (2022)