Optical Flow Training under Limited Label Budget via Active Learning. (arXiv:2203.05053v2 [cs.CV] UPDATED)

Supervised training of optical flow predictors generally yields better
accuracy than unsupervised training. However, the improved performance comes at
an often high annotation cost. Semi-supervised training trades off accuracy
against annotation cost. We use a simple yet effective semi-supervised training
method to show that even a small fraction of labels can improve flow accuracy
by a significant margin over unsupervised training. In addition, we propose
active learning methods based on simple heuristics to further reduce the number
of labels required …

active learning arxiv budget flow training