论文标题
类比学习：从不监督的光流估计转换的可靠监督
Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation
论文作者
论文摘要
利用视图综合监督的光流的无监督学习已成为监督方法的有希望的替代方法。但是，在具有挑战性的场景中，无监督学习的目标可能是不可靠的。在这项工作中，我们提出了一个框架，以使用转换中更可靠的监督。它简单地扭曲了一般无监督的学习管道，通过通过增强的转换数据运行另一个前向通行证，并使用对原始数据的转换预测作为自学信号。此外，我们进一步引入了一个由高度共享流量解码器多个帧的轻型网络。我们的方法始终在多个基准测试基准上取得了绩效的飞跃，在深度无监督的方法中的准确性最高。同样，我们的方法还可以实现竞争成果，以最新的全面监督方法，而参数却少得多。
Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods. However, the objective of unsupervised learning is likely to be unreliable in challenging scenes. In this work, we present a framework to use more reliable supervision from transformations. It simply twists the general unsupervised learning pipeline by running another forward pass with transformed data from augmentation, along with using transformed predictions of original data as the self-supervision signal. Besides, we further introduce a lightweight network with multiple frames by a highly-shared flow decoder. Our method consistently gets a leap of performance on several benchmarks with the best accuracy among deep unsupervised methods. Also, our method achieves competitive results to recent fully supervised methods while with much fewer parameters.
