FedCAug improves federated image classification by combining saliency-based object segmentation with random-background cut-paste augmentation, yielding small Top-1 accuracy improvements on NICO and ColorMNIST.
Clustering-based curriculum construction for sample-balanced federated learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Federated Out-of-Distribution Generalization: A Causal Augmentation View
FedCAug improves federated image classification by combining saliency-based object segmentation with random-background cut-paste augmentation, yielding small Top-1 accuracy improvements on NICO and ColorMNIST.