Cosegmentation Loss: Enhancing segmentation with a Few Training Samples by Transferring Region Knowledge to Unlabeled Images
Abstract: We treat semantic segmentation where a few pixel-wise labeled samples
and a large number of unlabeled samples are available. For this
situation we propose cosegmentation loss which enables us to transfer
the knowledge of a few pixel-wise labeled samples to a large number of
unlabeled images. In the experiments, we used human-part segmentation
with a few pixel-wise labeled images and 1715 unlabeled images, and
proved that the proposed co-segmentation loss helped make effective use
of unlabeled images.
TL;DR: Co-Segmentation Loss for semi-supervised semantic segmentation
Conflicts: uec.ac.jp
3 Replies
Loading