Improve object segmentation in video using an adaptive object proxy with AOP
Improve object segmentation in video using an adaptive object proxy with AOP
Towards Robust Video Object Segmentation with Adaptive Object Calibration
arXiv paper abstract https://arxiv.org/abs/2207.00887
arXiv PDF paper https://arxiv.org/pdf/2207.00887.pdf
... Semi-supervised video object segmentation (VOS) aims at segmenting objects in all target frames of a video, given annotated object masks of reference frames.
... existing methods ... neglecting object-level cues, pixel-level approaches make the tracking vulnerable to perturbations, and even indiscriminate among similar objects.
... propose ... First ... construct the object representations by applying an adaptive object proxy (AOP) aggregation method, where the proxies represent arbitrary-shaped segments at multi-levels for reference.
Then, prototype masks are initially generated from the reference-target correlations based on AOP. Afterwards ... calibrated through network modulation, conditioning on the object proxy representations.
... consolidate this conditional mask calibration process in a progressive manner, where the object representations and proto-masks evolve to be discriminative iteratively.
... achieves the state-of-the-art performance .... and ... superior robustness against perturbations ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
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
Comments