Segment objects in images with arbitrary text queries using OpenSeg
Segment objects in images with arbitrary text queries using OpenSeg
Open-Vocabulary Image Segmentation
arXiv paper abstract https://arxiv.org/abs/2112.12143v1
arXiv PDF paper https://arxiv.org/pdf/2112.12143v1.pdf
... design an open-vocabulary image segmentation model to organize an image into meaningful regions indicated by arbitrary texts.
... recent open-vocabulary models can not localize visual concepts well despite recognizing what are in an image.
... these models miss an important step of visual grouping, which organizes pixels into groups before learning visual-semantic alignments.
... propose OpenSeg ... learns to propose segmentation ... for possible organizations. Then it learns ... alignments ... each word in a caption to ... predicted masks.
... support learning from captions, making it possible to scale up the dataset and vocabulary sizes.
.. work is the first to perform zero-shot transfer on holdout segmentation datasets. ... outperforms these baselines ...
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
Comments