用伪标签训练+双模型级联，提升复杂视频目标分割精度
Pseudo-Label Enhanced Cascaded Framework: 2nd Technical Report for LSVOS 2025 VOS Track
- 训练时用SAM2生成伪标签，增强数据多样性
- 推理时融合SAM2Long与SeC模型，得分达0.8616
- 适合长视频中目标小、遮挡多的复杂场景
复杂视频目标分割在小目标、相似目标、频繁遮挡、快速运动和复杂交互等挑战下仍难以准确分割。本文针对LSVOS 2025 VOS赛道提出基于SAM2框架的解决方案。训练阶段，利用已训练的SAM2检查点在SAM2Long框架内为MOSE测试集生成伪标签，并与现有数据合并用于进一步训练。推理阶段，采用SAM2Long框架获取主分割结果，同时并行运行开源SeC模型生成互补预测。通过级联决策机制动态融合两模型输出，充分利用SAM2Long的时间稳定性与SeC的概念鲁棒性。得益于伪标签训练与级联多模型推理，本方法在MOSE测试集上取得J&F分数0.8616，较SAM2Long基线提升1.4分，位列2025年LSVOS VOS赛道第2名，在长视频复杂分割任务中展现出强鲁棒性与高精度。
原文摘要 · Abstract (English)
Complex Video Object Segmentation (VOS) presents significant challenges in accurately segmenting objects across frames, especially in the presence of small and similar targets, frequent occlusions, rapid motion, and complex interactions. In this report, we present our solution for the LSVOS 2025 VOS Track based on the SAM2 framework. We adopt a pseudo-labeling strategy during training: a trained SAM2 checkpoint is deployed within the SAM2Long framework to generate pseudo labels for the MOSE test set, which are then combined with existing data for further training. For inference, the SAM2Long framework is employed to obtain our primary segmentation results, while an open-source SeC model runs in parallel to produce complementary predictions. A cascaded decision mechanism dynamically integrates outputs from both models, exploiting the temporal stability of SAM2Long and the concept-level robustness of SeC. Benefiting from pseudo-label training and cascaded multi-model inference, our approach achieves a J\&F score of 0.8616 on the MOSE test set -- +1.4 points over our SAM2Long baseline -- securing the 2nd place in the LSVOS 2025 VOS Track, and demonstrating strong robustness and accuracy in long, complex video segmentation scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。