提升小物体跟踪在遮挡和重出现时的鲁棒性，不改主干只优化记忆控制。
OAMVOS:2nd Report for 5th PVUW MOSE Track
- 引入可靠性感知状态机与分支恢复机制，动态管理追踪状态。
- 延迟记忆更新、选择性使用原生记忆，显著提升长遮挡后重识别能力。
- 适合小物体密集遮挡场景，对视频目标分割任务有实用价值。
基于SAM的密集追踪器在短时掩码传播中表现强劲，但在长期遮挡、快速运动、视角变化和干扰物下仍显脆弱，尤其对小物体影响更严重——少量错误记忆更新即可主导后续预测。本报告提出OAMVOS，作为DAM4SAM的扩展，通过四类改进增强记忆控制能力：可靠性感知追踪状态机、分支式恢复策略、延迟的动态记忆提升（DRM）促进机制，以及原生SAM3记忆选择的有选择性策略。在稳定追踪阶段，沿用原有单路径传播流程；当置信度下降时，进入模糊或恢复模式，维护一组候选分支，仅在分支被重新确认后才提交记忆。针对小物体消失与重出现情况，临时跳过原生记忆选择，确保旧锚点可访问。同时，首帧条件信息被显式保留，条件记忆预算适度扩大以增强长间隙恢复能力。该设计在简单场景保持DAM4SAM高效性的同时，在以遮挡与重出现为主的序列中显著提升鲁棒性。
原文摘要 · Abstract (English)
SAM-based dense trackers provide strong short-term mask propagation but remain fragile under long occlusion, fast motion, viewpoint change, and distractors. The problem is especially severe for small objects, where a few incorrect memory updates can dominate later predictions. This report presents an occlusion- and reappearance-aware extension of DAM4SAM that improves memory control rather than changing the backbone. The method augments the original SAM3 tracker with four ingredients: a reliability-aware tracking state machine, branch-based recovery, delayed DRM promotion, and a selective policy for native SAM3 memory selection. During stable tracking, the model follows the original single-path propagation process. Once confidence drops, the tracker enters an ambiguous or recovery mode, maintains a small set of candidate branches, and commits memory only after a branch is reconfirmed. For small-object disappearance and reappearance, native memory selection is temporarily bypassed so older anchors remain accessible. In addition, the first conditioning frame is explicitly preserved, and the conditioning-memory budget is moderately enlarged to improve long-gap recovery. The resulting design keeps DAM4SAM efficient in easy cases while improving robustness in sequences dominated by occlusion and reappearance.
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。