CGFSeg通过融合多模型优势，实现复杂视频中目标的高精度分割。
The 1st Solution for MOSEv1 Challenge on LSVOS 2025: CGFSeg
- 冻结SAM2特征提取器，微调其余模块提升分割精度。
- 引入像素级校验策略，逐步优化预测结果，提升鲁棒性。
- 在MOSEv1挑战赛中取得J&F 86.37%的首名成绩，适合复杂场景应用。
视频对象分割（VOS）旨在追踪并分割视频序列中的特定对象，但在复杂真实场景下仍具挑战性。本次参与的MOSEv1挑战赛基于LVOS数据集，专为提升VOS模型在长时目标消失与重现、小而隐蔽目标等复杂场景下的鲁棒性设计。本文提出改进方法——置信度引导融合分割（CGFSeg）。训练阶段冻结SAM2的特征提取器，仅微调其余组件以保留强大特征提取能力并提升分割精度。推理阶段引入像素级校验策略，通过利用多个模型的互补优势逐步优化预测结果，从而生成稳健的最终掩码。最终方法在测试集上取得86.37%的J&F得分，位列LSVOS 2025 MOSEv1挑战赛第一，验证了其在复杂场景下解决VOS任务的有效性。
原文摘要 · Abstract (English)
Video Object Segmentation (VOS) aims to track and segment specific objects across entire video sequences, yet it remains highly challenging under complex real-world scenarios. The MOSEv1 and LVOS dataset, adopted in the MOSEv1 challenge on LSVOS 2025, which is specifically designed to enhance the robustness of VOS models in complex real-world scenarios, including long-term object disappearances and reappearances, as well as the presence of small and inconspicuous objects. In this paper, we present our improved method, Confidence-Guided Fusion Segmentation (CGFSeg), for the VOS task in the MOSEv1 Challenge. During training, the feature extractor of SAM2 is frozen, while the remaining components are fine-tuned to preserve strong feature extraction ability and improve segmentation accuracy. In the inference stage, we introduce a pixel-check strategy that progressively refines predictions by exploiting complementary strengths of multiple models, thereby yielding robust final masks. As a result, our method achieves a J&F score of 86.37% on the test set, ranking 1st in the MOSEv1 Challenge at LSVOS 2025. These results highlight the effectiveness of our approach in addressing the challenges of VOS task in complex 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。