Video object segmentation with adaptive feature bank and uncertain-region refinement
Document Type
Conference Proceeding
Publication Date
1-1-2020
Abstract
This paper presents a new matching-based framework for semi-supervised video object segmentation (VOS). Recently, state-of-the-art VOS performance has been achieved by matching-based algorithms, in which feature banks are created to store features for region matching and classification. However, how to effectively organize information in the continuously growing feature bank remains under-explored, and this leads to an inefficient design of the bank. We introduced an adaptive feature bank update scheme to dynamically absorb new features and discard obsolete features. We also designed a new confidence loss and a fine-grained segmentation module to enhance the segmentation accuracy in uncertain regions. On public benchmarks, our algorithm outperforms existing state-of-the-arts.
Publication Source (Journal or Book title)
Advances in Neural Information Processing Systems
Recommended Citation
Liang, Y., Li, X., Jafari, N., & Chen, Q. (2020). Video object segmentation with adaptive feature bank and uncertain-region refinement. Advances in Neural Information Processing Systems, 2020-December Retrieved from https://repository.lsu.edu/eecs_pubs/694
