ACSAN: All-Convolutional Self-Attention Network Integrating Convolutional Operations with Vision Transformer
Open paper
Benchmark
Model
Rank
Results
image-classification-on-imagenet
ACSAN-Base
–
Top 1 Accuracy: 82.7%
GFLOPs: 9.77
image-classification-on-imagenet
ACSAN-Large
–
Top 1 Accuracy: 82.8%
GFLOPs: 10.82
Rank counts only results with a code link.