Video Object Segmentation (VOS) task aims to segmenting a particular object instance throughout the entire video sequence given only the object mask of the first frame. Recently, Segment Anything Model 2 (SAM 2) is proposed, which is a foundation model towards solving promptable visual segmentation in images and videos. SAM 2 builds a data engine, which improves model and data via user interaction, to collect the largest video segmentation dataset to date. SAM 2 is a simple transformer architecture with streaming memory for real-time video processing, which trained on the date provides strong performance across a wide range of tasks. In this work, we evaluate the zero-shot performance of SAM 2 on the more challenging VOS datasets MOSE and LVOS. Without fine-tuning on the training set, SAM 2 achieved 75.79 J&F on the test set and ranked 4th place for 6th LSVOS Challenge VOS Track.
@article{arxiv.2408.10125,
title = {Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track},
author = {Feiyu Pan and Hao Fang and Runmin Cong and Wei Zhang and Xiankai Lu},
journal= {arXiv preprint arXiv:2408.10125},
year = {2024}
}
Comments
arXiv admin note: substantial text overlap with arXiv:2408.00714