Video Object Segmentation with Re-identification
This work improves video object segmentation for applications like video editing and surveillance by introducing a novel re-identification mechanism to handle challenging scenarios.
The paper tackled the problem of video object segmentation by addressing issues like drifting and large displacement through adaptive object re-identification, achieving a global mean score of 0.699 and the best performance in the 2017 DAVIS Challenge.
Conventional video segmentation methods often rely on temporal continuity to propagate masks. Such an assumption suffers from issues like drifting and inability to handle large displacement. To overcome these issues, we formulate an effective mechanism to prevent the target from being lost via adaptive object re-identification. Specifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module. The former module produces an initial probability map by flow warping while the latter module retrieves missing instances by adaptive matching. With these two modules iteratively applied, our VS-ReID records a global mean (Region Jaccard and Boundary F measure) of 0.699, the best performance in 2017 DAVIS Challenge.