The 2nd Solution for LSVOS Challenge RVOS Track: Spatial-temporal Refinement for Consistent Semantic Segmentation
This work addresses inconsistency issues in RVOS for video analysis applications, representing an incremental improvement by integrating an existing model (SAM-v2) into the pipeline.
The paper tackled the challenge of maintaining consistent semantic segmentation in Referring Video Object Segmentation (RVOS) over prolonged time sequences by leveraging SAM-v2 for tracking, achieving a score of 60.40 J&F on the MeViS dataset and placing 2nd in the RVOS Track at the ECCV 2024 LSVOS Challenge.
Referring Video Object Segmentation (RVOS) is a challenging task due to its requirement for temporal understanding. Due to the obstacle of computational complexity, many state-of-the-art models are trained on short time intervals. During testing, while these models can effectively process information over short time steps, they struggle to maintain consistent perception over prolonged time sequences, leading to inconsistencies in the resulting semantic segmentation masks. To address this challenge, we take a step further in this work by leveraging the tracking capabilities of the newly introduced Segment Anything Model version 2 (SAM-v2) to enhance the temporal consistency of the referring object segmentation model. Our method achieved a score of 60.40 \mathcal{J\text{\&}F} on the test set of the MeViS dataset, placing 2nd place in the final ranking of the RVOS Track at the ECCV 2024 LSVOS Challenge.