Improve object segmentation in video using object-agnostic information with DeAOT
Improve object segmentation in video using object-agnostic information with DeAOT
Decoupling Features in Hierarchical Propagation for Video Object Segmentation
arXiv paper abstract https://arxiv.org/abs/2210.09782v2
arXiv PDF paper https://arxiv.org/pdf/2210.09782v2.pdf
This paper focuses on developing a more effective method of hierarchical propagation for semi-supervised Video Object Segmentation (VOS).
... recently-developed Associating Objects with Transformers (AOT) ... hierarchical propagation ... will inevitably lead to the loss of object-agnostic visual information in deep propagation layers.
... paper proposes a Decoupling Features in Hierarchical Propagation (DeAOT) approach.
Firstly, DeAOT decouples the hierarchical propagation of object-agnostic and object-specific embeddings by handling them in two independent branches.
Secondly, to compensate for the additional computation from dual-branch propagation, ... propose an efficient module for constructing hierarchical propagation
... achieve new state-of-the-art performance on four benchmarks, i.e., YouTube-VOS (86.2%), DAVIS 2017 (86.2%), DAVIS 2016 (92.9%), and VOT 2020 (0.622) ...
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
#ComputerVision #Segmentation #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning
Comments