Dual Prototype Attention for Unsupervised Video Object Segmentation

TL;DR

This paper proposes two novel prototype-based attention mechanisms, inter-modality attention (IMA) and inter-frame attention (IFA), to incorporate these techniques via dense propagation across different modalities and frames.

Abstract

Unsupervised video object segmentation (VOS) aims to detect and segment the most salient object in videos. The primary techniques used in unsupervised VOS are 1) the collaboration of appearance and motion information; and 2) temporal fusion between different frames. This paper proposes two novel prototype-based attention mechanisms, inter-modality attention (IMA) and inter-frame attention (IFA), to incorporate these techniques via dense propagation across different modalities and frames. IMA densely integrates context information from different modalities based on a mutual refinement. IFA injects global context of a video to the query frame, enabling a full utilization of useful properties from multiple frames. Experimental results on public benchmark datasets demonstrate that our proposed approach outperforms all existing methods by a substantial margin. The proposed two components are also thoroughly validated via ablative study.

Figures (6)

• Figure 1: Visualized feature maps after applying IMA and IFA.
• Figure 2: Architecture of our proposed network. Based on a two-stream encoder-decoder architecture, IMA and IFA modules are employed. For simplicity, skip connections between encoding blocks and decoding blocks are omitted in the illustration.
• Figure 3: Visualized pipeline of IMA.
• Figure 4: Visualized pipeline of IFA.
• Figure 5: Visualized activation maps of different IMA versions.