Better image segmentation with few examples by using multiple relevant feature maps and with MSANet
--
Better image segmentation with few examples by using multiple relevant feature maps and with MSANet
MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation
arXiv paper abstract https://arxiv.org/abs/2206.09667v1
arXiv PDF paper https://arxiv.org/pdf/2206.09667v1.pdf
GitHub https://github.com/AIVResearch/MSANet
Few-shot segmentation aims to segment unseen-class objects given only a handful of densely labeled samples.
Prototype learning, where the support feature yields a single or several prototypes by averaging global and local object information, has been widely used in FSS.
… To extract abundant features … propose a Multi-Similarity and Attention Network (MSANet) including two novel modules, a multi-similarity module and an attention module.
The multi-similarity module exploits multiple feature-maps of support images and query images to estimate accurate semantic relationships.
The attention module instructs the network to concentrate on class-relevant information.
… achieves the state-of-the-art performance for all 4-benchmark datasets with mean intersection over union (mIoU) of 69.13%, 73.99%, 51.09%, 56.80%, respectively …
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
