`

Timezone: »

 
Poster
Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement
Yongqing Liang · Xin Li · Navid Jafari · Jim Chen

Tue Dec 08 09:00 PM -- 11:00 PM (PST) @ Poster Session 2 #627

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.

Author Information

Yongqing Liang (Louisiana State University)
Xin Li (Louisiana State University)
Navid Jafari (Louisiana State University)
Jim Chen (Northeastern University)