Segment scene unsupervised by clustering pseudo labels from self-supervised models with U2Seg
Segment scene unsupervised by clustering pseudo labels from self-supervised models with U2Seg
Unsupervised Universal Image Segmentation
arXiv paper abstract https://arxiv.org/abs/2312.17243
arXiv PDF paper https://arxiv.org/pdf/2312.17243.pdf
... unsupervised image segmentation ... eliminate the need for dense manually-annotated segmentation masks; current models separately handle either semantic segmentation (e.g., STEGO) or class-agnostic instance segmentation (e.g., CutLER), but not both (i.e., panoptic segmentation).
... propose an Unsupervised Universal Segmentation model (U2Seg) adept at performing various image segmentation tasks -- instance, semantic and panoptic -- using a novel unified framework.
U2Seg generates pseudo semantic labels for these segmentation tasks via leveraging self-supervised models followed by clustering; each cluster represents different semantic and/or instance membership of pixels.
... then self-train the model on these pseudo semantic labels, yielding substantial performance gains over specialized methods tailored to each task
... U2Seg is also a strong pretrained model for few-shot segmentation ... when trained on ... only 1% COCO labels ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comentários