论文标题
无监督的光流中的成本功能展开
Cost Function Unrolling in Unsupervised Optical Flow
论文作者
论文摘要
最陡峭的下降算法（通常用于深度学习），将梯度用作下降方向，无论是IS还是在方向移动后使用预处理。在许多情况下，由于复杂或非差异的成本函数，特别是在单数点附近，计算梯度在数值上很难。在这项工作中，我们着重于无监督成本函数中常用的总变异半正式的推导。具体而言，我们在一种新颖的迭代方案中得出了对硬L1平滑度约束的可区分代理，我们将其称为成本展开。我们的方法在训练过程中产生更准确的梯度，可以通过改进的收敛性来更好地预测给定的DNN模型，而无需修改其体系结构或提高计算复杂性。我们在无监督的光流任务中演示了我们的方法。在训练众所周知的基线期间，我们用我们的展开成本代替了L1平滑度约束，我们报告了MPI Sintel和Kitti 2015年无人监督的光流基准的改进结果。特别是，我们报告的EPE在封闭的像素上最多降低了15.82％，在该像素中，平滑度约束是主导的，从而可以检测到许多尖锐的运动边缘。
Steepest descent algorithms, which are commonly used in deep learning, use the gradient as the descent direction, either as-is or after a direction shift using preconditioning. In many scenarios calculating the gradient is numerically hard due to complex or non-differentiable cost functions, specifically next to singular points. In this work we focus on the derivation of the Total Variation semi-norm commonly used in unsupervised cost functions. Specifically, we derive a differentiable proxy to the hard L1 smoothness constraint in a novel iterative scheme which we refer to as Cost Unrolling. Producing more accurate gradients during training, our method enables finer predictions of a given DNN model through improved convergence, without modifying its architecture or increasing computational complexity. We demonstrate our method in the unsupervised optical flow task. Replacing the L1 smoothness constraint with our unrolled cost during the training of a well known baseline, we report improved results on both MPI Sintel and KITTI 2015 unsupervised optical flow benchmarks. Particularly, we report EPE reduced by up to 15.82% on occluded pixels, where the smoothness constraint is dominant, enabling the detection of much sharper motion edges.
