Better image segmentation of details by using multiple image crops with CropFormer

Better image segmentation of details by using multiple image crops with CropFormer

Fine-Grained Entity Segmentation
arXiv paper abstract https://arxiv.org/abs/2211.05776
arXiv PDF paper https://arxiv.org/pdf/2211.05776.pdf
GitHub https://github.com/dvlab-research/Entity
Project page http://luqi.info/entityv2.github.io

In dense image segmentation tasks (e.g., semantic, panoptic), existing methods can hardly generalize well to unseen image domains, predefined classes, and image resolution & quality variations.

… construct a large-scale entity segmentation dataset to explore fine-grained entity segmentation, with a strong focus on open-world and high-quality dense segmentation.

The dataset contains images spanning diverse image domains and resolutions, along with high-quality mask annotations for training and testing.

… propose CropFormer for high-quality segmentation, which can improve mask prediction using high-res image crops that provide more fine-grained image details than the full image.

CropFormer is the first query-based Transformer architecture that can effectively ensemble mask predictions from multiple image crops, by learning queries that can associate the same entities across the full image and its crop.

… achieve a significant AP gain of 1.9 on the challenging fine-grained entity segmentation task …

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

LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b