Paper: SiamPolar: Semi-supervised realtime video object segmentation with polar representation
arXiv: https://arxiv.org/abs/2110.14773
Code: https://github.com/JosieHong/SiamPolar
SiamPolar is a semi-supervised real-time video object segmentation method with a novel polar representation method. The input of bounding boxes is initialized rather than the object masks, which are applied to the video object detection tasks. The polar representation could reduce the parameters for encoding masks with subtle accuracy loss so that the algorithm speed can be improved significantly. An asymmetric siamese network is also developed to extract the features from different spatial scales. Moreover, the peeling convolution is proposed to reduce the antagonism among the branches of the polar head. The repeated cross-correlation and semi-FPN are designed based on this idea.
computer vision — Jun 22, 2021
Made with ❤ and at Earth.