Transferring Dense Pose to Proximal Animal Classes

Figure 1 : We consider the problem of dense pose labelling in animal classes. We show that, for proximal to humans classes such as chimpanzees (left), we can obtain excellent performance by learning an integrated recognition architecture from existing data sources, including DensePose for humans as well as detection and segmentation information from other COCO classes (right). The key is to establish a common reference (middle), which we obtain via alignment of the reference models of the animals. This enables training a model for the target class without having to label a single example image for it. Source image credit, on the left: [52, 48, 42, 57, 60, 34] , on the right: COCO dataset [29].