We propose a technique to train semantic part-based models of object classes from Google Images. Our models encompass the appearance of parts and their spatial arrangement on the object, specific to each viewpoint. We learn these rich models by collecting training instances for both parts and objects, and automatically connecting the two levels. Our framework works incrementally, by learning from easy examples first, and then gradually adapting to harder ones. A key benefit of this approach is that it requires no manual part location annotations. We evaluate our models on the challenging PASCAL-Part dataset [1] and show how their performance increases at every step of the learning, with the final models more than doubling the performance of directly training from images retrieved by querying for part names (from 12.9 to 27.2 AP). Moreover, we show that our part models can help object detection performance by enriching the R-CNN detector with parts.

中文翻译：

---

从Google图片学习基于语义的基于零件的模型

我们提出了一种从Google图像训练对象类的基于语义部分的模型的技术。我们的模型包含零件的外观及其在对象上的空间排列，特定于每个视点。我们通过收集零件和对象的训练实例并自动连接两个级别来学习这些丰富的模型。我们的框架通过首先学习简单的示例，然后逐渐适应较难的示例而逐步工作。这种方法的主要优点是不需要手动零件位置注释。我们在具有挑战性的PASCAL-Part数据集上评估我们的模型 [1]并展示了它们在学习的每个步骤中的性能如何提高，最终的模型使通过查询零件名称（从12.9到27.2 AP）从检索到的图像中直接训练的性能提高了一倍以上。此外，我们证明了我们的零件模型可以通过用零件丰富R-CNN检测器来帮助目标检测性能。