State of the art human pose estimation models continue to rely on large quantities of labelled data for robust performance. Since labelling budget is often constrained, active learning algorithms are important in retaining the overall performance of the model at a lower cost. Although active learning has been well studied in literature, few techniques are reported for human pose estimation. In this paper, we theoretically derive expected gradient length for regression, and propose EGL++, a novel heuristic algorithm that extends expected gradient length to tasks where discrete labels are not available. We achieve this by computing low dimensional representations of the original images which are then used to form a neighborhood graph. We use this graph to: 1) Obtain a set of neighbors for a given sample, with each neighbor iteratively assumed to represent the ground truth for gradient calculation 2) Quantify the probability of each sample being a neighbor in the above set, facilitating the expected gradient step. Such an approach allows us to provide an approximate solution to the otherwise intractable task of integrating over the continuous output domain. To validate EGL++, we use the same datasets (Leeds Sports Pose, MPII) and experimental design as suggested by previous literature, achieving competitive results in comparison to these methods.
翻译:由于标签预算经常受到限制,积极学习算法对于以较低成本保持模型的整体性能很重要。虽然积极学习在文献中研究过,但很少报告人类构成估计技术。在本文中,我们理论上得出回归的预期梯度长度,并提议EGL++,这是一种将预期梯度长度延伸至无法提供离散标签的任务的新的超自然算法。我们通过计算原始图像的低维表示法来实现这一点,然后用这些图像来形成相邻图。我们使用这个图解来:1)为某一样本获得一套邻居,每个邻居反复假定代表梯度计算地面真实性。2)量化每个样本作为上一组中邻居的可能性,便利预期梯度步骤。这种方法使我们能够为连续输出域的整合这一本来难以完成的任务提供大致的解决办法。为了验证EGL++,我们使用相同的数据集(Leeds Sport Pose, MPII)和实验设计方法,以这些方法进行比较。