Segment object with few examples using multi-level prototype generation with Bao
Segment object with few examples using multi-level prototype generation with Bao
Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation
arXiv paper abstract https://arxiv.org/abs/2312.06474
arXiv PDF paper https://arxiv.org/pdf/2312.06474.pdf
For few-shot semantic segmentation, the primary task is to extract class-specific intrinsic information from limited labeled data.
… semantic ambiguity and inter-class similarity of previous methods limit the accuracy of pixel-level foreground-background classification … propose the Relevant Intrinsic Feature Enhancement Network (RiFeNet).
To improve the semantic consistency of foreground instances, … propose an unlabeled branch as an efficient data utilization method, which teaches the model how to extract intrinsic features robust to intra-class differences.
Notably, during testing, the proposed unlabeled branch is excluded without extra unlabeled data and computation.
… extend the inter-class variability between foreground and background by proposing a novel multi-level prototype generation and interaction module.
… RiFeNet surpasses the state-of-the-art methods on PASCAL-5i and COCO benchmarks.
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
