Improving Few-Shot Part Segmentation using Coarse Supervision. (arXiv:2204.05393v2 [cs.CV] UPDATED)

A significant bottleneck in training deep networks for part segmentation is
the cost of obtaining detailed annotations. We propose a framework to exploit
coarse labels such as figure-ground masks and keypoint locations that are
readily available for some categories to improve part segmentation models. A
key challenge is that these annotations were collected for different tasks and
with different labeling styles and cannot be readily mapped to the part labels.
To this end, we propose to jointly learn the dependencies …

arxiv cv part segmentation