Table 9 Accuracy comparison of EMNIST classification.
From: Deep representation learning using layer-wise VICReg losses
Num. of sample | Linear (%) | Baseline (%) | Fine-tuned (%) |
|---|---|---|---|
1000 | 40.68 | 40.52 | 56.71 |
1500 | 42.71 | 42.26 | 59.03 |
2000 | 44.65 | 58.85 | 63.01 |
5000 | 47.10 | 70.94 | 71.59 |
9400 | 51.33 | 75.18 | 75.62 |
