FixMatch

2000년 도입 · 논문 85편에서 사용

FixMatch is an algorithm that first generates pseudo-labels using the model's predictions on weakly-augmented unlabeled images. For a given image, the pseudo-label is only retained if the model produces a high-confidence prediction. The model is then trained to predict the pseudo-label when fed a strongly-augmented version of the same image. Description from: FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence Image credit: FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

출처: FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

소개 논문: FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence