International Journal of Interdisciplinary Research
From: Conceptual framework of hybrid style in fashion image datasets for machine learning
Model | Top-1 accuracy (%) | Top-3 accuracy (%) | Top-5 accuracy (%) | Top-3 sub label ratio (%) | Top-5 sub label ratio (%) |
---|---|---|---|---|---|
Big transfer ResNetV2 | 61.29 | 84.65 | 93.49 | 65.06 | 78.21 |
EifficientNet | 61.19 | 85.44 | 93.37 | 63.96 | 78.20 |
Vision transformer | 75.21 | 93.93 | 97.22 | 57.30 | 69.45 |