SAG-ViT

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Image ClassificationonNCT-CRC-HE-100K
F1· 2024-11-14
98.61
SOTA
SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers arXiv:2411.09420
Image ClassificationonGTSRB
F1· 2024-11-14
99.58
SOTA
SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers arXiv:2411.09420
Image ClassificationonRESISC45
F1· 2024-11-14
95.49
SOTA
SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers arXiv:2411.09420
Image ClassificationonCIFAR-10
F1· 2024-11-14
95.74
SOTA
SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers arXiv:2411.09420