all AI news
SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization. (arXiv:2208.10128v1 [cs.CV])
cs.CV updates on arXiv.org arxiv.org
Matching-based methods, especially those based on space-time memory, are
significantly ahead of other solutions in semi-supervised video object
segmentation (VOS). However, continuously growing and redundant template
features lead to an inefficient inference. To alleviate this, we propose a
novel Sequential Weighted Expectation-Maximization (SWEM) network to greatly
reduce the redundancy of memory features. Different from the previous methods
which only detect feature redundancy between frames, SWEM merges both
intra-frame and inter-frame similar features by leveraging the sequential
weighted EM algorithm. Further, …
arxiv cv expectation-maximization real-time segmentation time video