Table 12 Accuracy comparison of fashion MNIST classification.
From: Deep representation learning using layer-wise VICReg losses
Num. of sample | Linear (%) | Baseline (%) | Fine-tuned (%) |
|---|---|---|---|
500 | 55.22 | 76.77 | 77.49 |
1000 | 61.48 | 79.37 | 79.88 |
2500 | 66.75 | 82.05 | 82.57 |
5000 | 66.17 | 83.66 | 83.65 |
