由人的密集姿势识别转移到邻近动物类识别(CS.CV)

• 2020 年 3 月 27 日
• 筆記

最新的研究表明，给定详细注释的大型姿势数据集，可以密集而准确地识别人的姿势。原则上，相同的方法可以扩展到任何动物类别，但是尽管在自然保护，科学和商业中有重要应用，但为每种情况收集新注释所需的工作使该策略不切实际。我们表明，至少对于邻近动物类别（如黑猩猩），可以将人类密集姿势识别以及更一般的对象检测器和分割器中存在的知识转移到其他类别的密集姿势识别问题中。为此，我们（1）为新动物建立了DensePose模型，该模型在几何上也与人类保持一致；（2）引入了多头R-CNN架构，该架构有助于在类之间转移多个识别任务；（3）查找哪种组合已知类别的样本可以最有效地转移到新动物上；（4）使用自校准不确定度头生成按质量分级的伪标签，以训练该类别的模型。我们还为黑猩猩引入了两个以DensePose方式标记的基准数据集，并使用它们评估了我们的方法，显示了出色的迁移学习性能。

原文题目：Transferring Dense Pose to Proximal Animal Classes

原文：Recent contributions have demonstrated that it is possible to recognize the pose of humans densely and accurately given a large dataset of poses annotated in detail. In principle, the same approach could be extended to any animal class, but the effort required for collecting new annotations for each case makes this strategy impractical, despite important applications in natural conservation, science and business. We show that, at least for proximal animal classes such as chimpanzees, it is possible to transfer the knowledge existing in dense pose recognition for humans, as well as in more general object detectors and segmenters, to the problem of dense pose recognition in other classes. We do this by (1) establishing a DensePose model for the new animal which is also geometrically aligned to humans (2) introducing a multi-head R-CNN architecture that facilitates transfer of multiple recognition tasks between classes, (3) finding which combination of known classes can be transferred most effectively to the new animal and (4) using self-calibrated uncertainty heads to generate pseudo-labels graded by quality for training a model for this class. We also introduce two benchmark datasets labelled in the manner of DensePose for the class chimpanzee and use them to evaluate our approach, showing excellent transfer learning performance.

原文作者：Artsiom Sanakoyeu, Vasil Khalidov, Maureen S. McCarthy, Andrea Vedaldi, Natalia Neverova

原文地址：https://arxiv.org/abs/2003.00080