Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement
This work addresses inefficiencies in video object segmentation for computer vision applications, representing an incremental improvement.
The paper tackled the problem of inefficient feature bank organization in matching-based video object segmentation by introducing an adaptive update scheme and uncertain-region refinement, achieving state-of-the-art performance on public benchmarks.
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.