Unsupervised video object segmentation aims to segment the most prominent object in a video sequence. However, the existence of complex backgrounds and multiple foreground objects make this task challenging. To address this issue, we propose a guided slot attention network to reinforce spatial structural information and obtain better foreground--background separation. The foreground and background slots, which are initialized with query guidance, are iteratively refined based on interactions with template information. Furthermore, to improve slot--template interaction and effectively fuse global and local features in the target and reference frames, K-nearest neighbors filtering and a feature aggregation transformer are introduced. The proposed model achieves state-of-the-art performance on two popular datasets. Additionally, we demonstrate the robustness of the proposed model in challenging scenes through various comparative experiments.
@article{arxiv.2303.08314,
title = {Guided Slot Attention for Unsupervised Video Object Segmentation},
author = {Minhyeok Lee and Suhwan Cho and Dogyoon Lee and Chaewon Park and Jungho Lee and Sangyoun Lee},
journal= {arXiv preprint arXiv:2303.08314},
year = {2024}
}