Human-inspired Global-to-Parallel Multi-scale Encoding for Lightweight Vision Models
Open paper
Benchmark
Model
Rank
Results
image-classification-on-imagenet
H-GPE-N
–
Top 1 Accuracy: 73.7%
image-classification-on-imagenet
H-GPE-S
–
Top 1 Accuracy: 79.1%
image-classification-on-imagenet
H-GPE-T
–
Top 1 Accuracy: 76.6%
Rank counts only results with a code link.