Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track
This work addresses video object segmentation for computer vision researchers, but it is incremental as it applies an existing foundation model to new datasets without modifications.
The paper tackled video object segmentation by evaluating the zero-shot performance of Segment Anything Model 2 (SAM 2) on challenging datasets MOSE and LVOS, achieving a J&F score of 75.79 and ranking 4th in the LSVOS Challenge VOS Track without fine-tuning.
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.