Guardado en:
Detalles Bibliográficos
Autores principales: Soliman, Mahmoud, Abdelaziz, Omar, Radwan, Ahmed, Anand, Shehata, Mohamed
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.04008
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912690165776384
author Soliman, Mahmoud
Abdelaziz, Omar
Radwan, Ahmed
Anand
Shehata, Mohamed
author_facet Soliman, Mahmoud
Abdelaziz, Omar
Radwan, Ahmed
Anand
Shehata, Mohamed
contents Domain generalization (DG) seeks robust Vision Transformer (ViT) performance on unseen domains. Efficiently adapting pretrained ViTs for DG is challenging; standard fine-tuning is costly and can impair generalization. We propose GNN-MoE, enhancing Parameter-Efficient Fine-Tuning (PEFT) for DG with a Mixture-of-Experts (MoE) framework using efficient Kronecker adapters. Instead of token-based routing, a novel Graph Neural Network (GNN) router (GCN, GAT, SAGE) operates on inter-patch graphs to dynamically assign patches to specialized experts. This context-aware GNN routing leverages inter-patch relationships for better adaptation to domain shifts. GNN-MoE achieves state-of-the-art or competitive DG benchmark performance with high parameter efficiency, highlighting the utility of graph-based contextual routing for robust, lightweight DG.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04008
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GNN-MoE: Context-Aware Patch Routing using GNNs for Parameter-Efficient Domain Generalization
Soliman, Mahmoud
Abdelaziz, Omar
Radwan, Ahmed
Anand
Shehata, Mohamed
Computer Vision and Pattern Recognition
Domain generalization (DG) seeks robust Vision Transformer (ViT) performance on unseen domains. Efficiently adapting pretrained ViTs for DG is challenging; standard fine-tuning is costly and can impair generalization. We propose GNN-MoE, enhancing Parameter-Efficient Fine-Tuning (PEFT) for DG with a Mixture-of-Experts (MoE) framework using efficient Kronecker adapters. Instead of token-based routing, a novel Graph Neural Network (GNN) router (GCN, GAT, SAGE) operates on inter-patch graphs to dynamically assign patches to specialized experts. This context-aware GNN routing leverages inter-patch relationships for better adaptation to domain shifts. GNN-MoE achieves state-of-the-art or competitive DG benchmark performance with high parameter efficiency, highlighting the utility of graph-based contextual routing for robust, lightweight DG.
title GNN-MoE: Context-Aware Patch Routing using GNNs for Parameter-Efficient Domain Generalization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.04008