PACS

Dataset Card for PACS PACS is an image dataset for domain generalization. It consists of four domains, namely Photo (1,670 images), Art Painting (2,048 images), Cartoon (2,344 images), and Sketch (3,929 images). Each domain contains seven categories (labels): Dog, Elephant, Giraffe, Guitar, Horse, and Person. The total

Papers using PACS (11)

Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalization2024 · 7 citesMitigating Domain Shift in Federated Learning via Intra- and Inter-Domain Prototypes2025 · 1 citesFederated Domain Generalization with Data-free On-server Matching Gradient2025 · 1 citesMulti-Modal Style Transfer-based Prompt Tuning for Efficient Federated Domain Generalization2026FedSDAF: Leveraging Source Domain Awareness for Enhanced Federated Domain Generalization2025Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training2024PARDON: Privacy-Aware and Robust Federated Domain Generalization2024Federated Unsupervised Domain Generalization using Global and Local Alignment of Gradients2024FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning2023 · 19 citesHypernetwork-Driven Model Fusion for Federated Domain Generalization2024FedCCRL: Federated Domain Generalization with Cross-Client Representation Learning2024