AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915523997990912 |
|---|---|
| author | Gedik, Hakan Emre Martin, Andrew Munir, Mustafa Baser, Oguzhan Marculescu, Radu Chinchali, Sandeep P. Bovik, Alan C. |
| author_facet | Gedik, Hakan Emre Martin, Andrew Munir, Mustafa Baser, Oguzhan Marculescu, Radu Chinchali, Sandeep P. Bovik, Alan C. |
| contents | Vision Graph Neural Networks (ViGs) have demonstrated promising performance in image recognition tasks against Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). An essential part of the ViG framework is the node-neighbor feature aggregation method. Although various graph convolution methods, such as Max-Relative, EdgeConv, GIN, and GraphSAGE, have been explored, a versatile aggregation method that effectively captures complex node-neighbor relationships without requiring architecture-specific refinements is needed. To address this gap, we propose a cross-attention-based aggregation method in which the query projections come from the node, while the key projections come from its neighbors. Additionally, we introduce a novel architecture called AttentionViG that uses the proposed cross-attention aggregation scheme to conduct non-local message passing. We evaluated the image recognition performance of AttentionViG on the ImageNet-1K benchmark, where it achieved SOTA performance. Additionally, we assessed its transferability to downstream tasks, including object detection and instance segmentation on MS COCO 2017, as well as semantic segmentation on ADE20K. Our results demonstrate that the proposed method not only achieves strong performance, but also maintains efficiency, delivering competitive accuracy with comparable FLOPs to prior vision GNN architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25570 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs Gedik, Hakan Emre Martin, Andrew Munir, Mustafa Baser, Oguzhan Marculescu, Radu Chinchali, Sandeep P. Bovik, Alan C. Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing Vision Graph Neural Networks (ViGs) have demonstrated promising performance in image recognition tasks against Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). An essential part of the ViG framework is the node-neighbor feature aggregation method. Although various graph convolution methods, such as Max-Relative, EdgeConv, GIN, and GraphSAGE, have been explored, a versatile aggregation method that effectively captures complex node-neighbor relationships without requiring architecture-specific refinements is needed. To address this gap, we propose a cross-attention-based aggregation method in which the query projections come from the node, while the key projections come from its neighbors. Additionally, we introduce a novel architecture called AttentionViG that uses the proposed cross-attention aggregation scheme to conduct non-local message passing. We evaluated the image recognition performance of AttentionViG on the ImageNet-1K benchmark, where it achieved SOTA performance. Additionally, we assessed its transferability to downstream tasks, including object detection and instance segmentation on MS COCO 2017, as well as semantic segmentation on ADE20K. Our results demonstrate that the proposed method not only achieves strong performance, but also maintains efficiency, delivering competitive accuracy with comparable FLOPs to prior vision GNN architectures. |
| title | AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Image and Video Processing |
| url | https://arxiv.org/abs/2509.25570 |