Image Classification on ImageNet 1% label fraction 2012 (val)
90Top-5 AccSimMatchV2
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SimMatchV2Pre-training Algorithm=None, Semi-supervised Algorithm=SimMatchV2 (Ours), Semi-supervised Epochs=~300, Parameters train=28.0M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 90 | 71.9 | |
| SimMatchV2Pre-training Algorithm=None, Semi-supervised Algorithm=SimMatchV2 (Ours), Semi-supervised Epochs=~100, Parameters train=28.0M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 88.7 | 69.9 | |
| SimMatchPre-training Algorithm=None, Semi-supervised Algorithm=SimMatch, Semi-supervised Epochs=~400, Parameters train=28.0M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 87.1 | 67.2 | |
| CoMatchPre-training Algorithm=None, Semi-supervised Algorithm=CoMatch, Semi-supervised Epochs=~400, Parameters train=28.0M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 86.4 | 66 | |
| WCLPre-training Algorithm=WCL, Semi-supervised Algorithm=Fine-tune, Pre-training Epochs=~800, Semi-supervised Epochs=~60, Parameters train=32.2M, Parameters inference=29.8M, Backbone=ResNet-502023.08 | 86.3 | 65 | |
| SSCLPre-training Algorithm=None, Semi-supervised Algorithm=SSCL, Semi-supervised Epochs=~800, Parameters train=28.0M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 82.8 | 60.2 | |
| SimCLR V2Pre-training Algorithm=SimCLR V2, Semi-supervised Algorithm=Fine-tune, Pre-training Epochs=~800, Semi-supervised Epochs=~60, Parameters train=32.2M, Parameters inference=29.8M, Backbone=ResNet-502023.08 | 82.5 | 57.9 | |
| MoCo V2 (FixMatch-EMAN)Pre-training Algorithm=MoCo V2, Semi-supervised Algorithm=FixMatch-EMAN, Pre-training Epochs=~800, Semi-supervised Epochs=~300, Parameters train=28.0M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 82.1 | 61.4 | |
| SWAVPre-training Algorithm=SWAV, Semi-supervised Algorithm=Fine-tune, Pre-training Epochs=~800, Semi-supervised Epochs=~20, Parameters train=28.0M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 78.5 | 53.9 | |
| BYOLPre-training Algorithm=BYOL, Semi-supervised Algorithm=Fine-tune, Pre-training Epochs=~1000, Semi-supervised Epochs=~50, Parameters train=35.1M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 78.4 | 53.2 | |
| MoCo V2 (Fine-tune)Pre-training Algorithm=MoCo V2, Semi-supervised Algorithm=Fine-tune, Pre-training Epochs=~800, Semi-supervised Epochs=~20, Parameters train=28.0M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 77.2 | 49.8 | |
| SimCLRPre-training Algorithm=SimCLR, Semi-supervised Algorithm=Fine-tune, Pre-training Epochs=~1000, Semi-supervised Epochs=~60, Parameters train=28.0M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 75.5 | 48.3 | |
| PCLPre-training Algorithm=PCL, Semi-supervised Algorithm=Fine-tune, Pre-training Epochs=~200, Semi-supervised Epochs=~20, Parameters train=23.8M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 75.3 | — | |
| S4L-RotationPre-training Algorithm=None, Semi-supervised Algorithm=S4L-Rotation, Semi-supervised Epochs=~200, Parameters train=25.6M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 53.4 | — | |
| VAT+EntMin.Pre-training Algorithm=None, Semi-supervised Algorithm=VAT+EntMin., Semi-supervised Epochs=~100, Parameters train=25.6M, Parameters inference=25.6M, Backbone=ResNet-502023.08 | 47 | — | |
| PAWSPre-training Algorithm=PAWS, Semi-supervised Algorithm=Fine-tune, Pre-training Epochs=~300, Semi-supervised Epochs=~50, Parameters train=36.1M, Parameters inference=29.8M, Backbone=ResNet-502023.08 | — | 66.5 |