Better object segmentation in video by using only high quality memorized frames with QDMN
Better object segmentation in video by using only high quality memorized frames with QDMN
Learning Quality-aware Dynamic Memory for Video Object Segmentation
arXiv paper abstract https://arxiv.org/abs/2207.07922v1
arXiv PDF paper https://arxiv.org/pdf/2207.07922v1.pdf
GitHub https://github.com/workforai/qdmn
… several spatial-temporal memory-based methods have verified that storing intermediate frames and their masks as memory are helpful to segment target objects in videos.
However, they … focus on … matching between the current … and … memory frames without … paying attention to the quality of the memory.
Therefore, frames with poor segmentation masks are prone to be memorized, which leads to a segmentation mask error accumulation problem
… propose a Quality-aware Dynamic Memory Network (QDMN) to evaluate the segmentation quality of each frame, allowing the memory bank to selectively store accurately segmented frames to prevent the error accumulation problem.
… QDMN achieves new state-of-the-art performance on both DAVIS and YouTube-VOS 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
