arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.05053cs.CV
收藏

基于主动学习的有限标记预算光流训练

Optical Flow Training under Limited Label Budget via Active Learning

Duke University(杜克大学)

Shuai Yuan, Xian Sun, Hannah Kim, Shuzhi Yu, Carlo Tomasi

摘要:

光流预测器的监督训练通常比无监督训练产生更好的准确性。然而,改进的性能通常伴随着较高的注释成本。半监督训练权衡了准确性和注释成本。我们使用一种简单而有效的半监督训练方法来证明,即使是一小部分标签也可以在无监督训练的基础上显著提高流的准确性。此外,我们还提出了基于简单算法的主动学习方法,以进一步减少达到相同目标精度所需的标签数量。我们在合成和真实光流数据集上的实验表明,我们的半监督网络通常需要大约50%的标签才能达到接近全标签的准确度,而在Sintel上使用主动学习只需要大约20%。我们还分析了可能影响主动学习表现的因素,并提出了见解。代码可在https://github.com/duke-vision/optical-flow-active-learning-release上获得。

英文摘要:

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 to achieve the same target accuracy. Our experiments on both synthetic and real optical flow datasets show that our semi-supervised networks generally need around 50% of the labels to achieve close to full-label accuracy, and only around 20% with active learning on Sintel. We also analyze and show insights on the factors that may influence active learning performance. Code is available at https://github.com/duke-vision/optical-flow-active-learning-release.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑