Models that learn to segment each image (i.e. cluster the pixels into their ground truth classes) without seeing the ground truth labels.
( Image credit: SegSort: Segmentation by Discriminative Sorting of Segments )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
The method is not specialised to computer vision and operates on any paired dataset samples; in our experiments we use random transforms to obtain a pair from each image.
As a result, we present the SegSort, as a first attempt using deep learning for unsupervised semantic segmentation, achieving $76\%$ performance of its supervised counterpart.
SOTA for Unsupervised Semantic Segmentation on PASCAL VOC 2012 val (using extra training data)
This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation.