Abstract | ||
---|---|---|
We propose 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 inefficient design of the bank. We introduce an adaptive feature bank update scheme to dynamically absorb new features and discard obsolete features. We also design 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. |
Year | Venue | DocType |
---|---|---|
2020 | NIPS 2020 | Conference |
Volume | ISSN | Citations |
33 | NeurIPS 2020 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
YongQing Liang | 1 | 2 | 2.41 |
Xin Li | 2 | 65 | 10.73 |
Navid Jafari | 3 | 0 | 1.69 |
Jim Chen | 4 | 3 | 4.46 |