Percentage error: 4.35±0.10
Papers with Code · CC BY-SA 4.0
Semi-Supervised Image Classification
Semi-supervised image classification leverages unlabelled data as well as labelled data to increase classification performance.
You may want to read some blog posts to get an overview before reading the papers and checking the leaderboards:
- An overview of proxy-label approaches for semi-supervised learning - Sebastian Ruder
- Semi-Supervised Learning in Computer Vision - Amit Chaudhary
<span style="color:grey; opacity: 0.6">( Image credit: Self-Supervised Semi-Supervised Learning )</span>
논문
Percentage error: 4.11±0.02
Percentage error: 1.41±0.10
Percentage error: 6.05±0.12
Percentage error: 3.8±0.08
Percentage error: 4.16
Percentage error: 4.08±0.06
Percentage error: 3.26±0.06
Percentage error: 5.79
Percentage error: 4.65±0.17
Percentage error: 4.23±0.20
Percentage error: 4.18
Percentage error: 4.31
Percentage error: 4.19±0.01
Percentage error: 4.86
Percentage error: 3.89± 0.07
Percentage error: 5.14
Percentage error: 5.72
Percentage error: 4.09
Percentage error: 4.06±0.08
Overall Accuracy: 97.24
Percentage error: 4.0 ± 0.25
Percentage error: 6.11
Percentage error: 3.96
Percentage error: 5
Percentage error: 5.27