Table 2 Test accuracy [%] (top-1) comparison between SCFF and self-supervised Learning methods on MNIST, CIFAR-10, STL-10, and Tiny ImageNet datasets

SimCLR (Chen et al. 2020⁷⁵)

✗

✓

–

94.0

89.7

53.4⁹²

Bio-SSL (Tang et al. 2022⁷⁸)

✓

✓

–

72.7

68.8

–

PNN-SSL (Laydevant et al. 2023⁷⁷)

✗

✗

96.6

77.0

–

–

CLAPP (Illing et al. 2021¹⁷)

✓

✓

–

–

73.6

–

SCFF (ours)

✓

✓

98.7

80.8

77.3

35.7