Better object segmentation of unknown objects using region awareness with RAML
Better object segmentation of unknown objects using region awareness with RAML
Region-Aware Metric Learning for Open World Semantic Segmentation via Meta-Channel Aggregation
arXiv paper abstract https://arxiv.org/abs/2205.08083v1
arXiv PDF paper https://arxiv.org/pdf/2205.08083v1.pdf
As one of the most challenging and practical segmentation tasks, open-world semantic segmentation requires the model to segment the anomaly regions in the images and incrementally learn to segment out-of-distribution (OOD) objects, especially under a few-shot condition.
… state-of-the-art … Deep Metric Learning Network (DMLNet), relies on pixel-level metric learning … identification of similar regions having different semantics is difficult.
… propose … region-aware metric learning (RAML), which first separates the regions of the images and generates region-aware features for further metric learning.
… propose a novel meta-channel aggregation (MCA) module to further separate anomaly regions, forming high-quality sub-region candidates and thereby improving the model performance for OOD objects.
… conducted … experiments and ablation studies on … datasets for anomaly segmentation and .. for incremental few-shot learning.
… show that the proposed RAML achieves SOTA performance in both stages of open world segmentation. …
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
