用于鲁棒视频目标分割的竞争性记忆读出：第8届LSVOS挑战赛MOSEv2赛道第2名技术报告

中文摘要 AI 辅助

我们展示了针对ECCV 2026第8届大规模视频目标分割（LSVOS）挑战赛MOSEv2赛道的解决方案。该挑战赛评估复杂时序动态下的鲁棒视频目标分割能力，包括长期遮挡、消失与重现、外观大幅变化，以及来自视觉相似对象的强干扰。我们的方法基于SAM~3模型，聚焦其记忆读出环节。仅针对目标的标准记忆检索会将标注目标与同类非目标对象混淆，因为此类干扰项仅作为背景被隐式表示。我们的方法引入竞争性记忆读出机制，在从记忆中检索目标信息时明确纳入同类竞争对象的证据。为防止对弱目标或重现目标的过度抑制，我们在竞争后进一步应用轻量自适应恢复规则。所得系统保留了原始SAM~3跟踪流程，同时提升了挑战性视频中的目标身份保持能力。我们的提交在挑战赛主评分中取得66.20分，在MOSEv2赛道排名第2。

英文摘要

We present our solution for the MOSEv2 track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge at ECCV 2026. The challenge evaluates robust video object segmentation under complex temporal dynamics, including long-term occlusion, disappearance and reappearance, large appearance changes, and strong interference from visually similar objects. Our method builds on SAM~3 and focuses on its memory readout. Standard target-only memory retrieval can confuse the annotated target with same-class non-target objects because such distractors are represented only implicitly as background. Our method introduces Competitive Memory Readout, which explicitly incorporates same-class competitor evidence when retrieving target information from memory. To prevent excessive suppression of weak or reappearing targets, we further apply a lightweight adaptive restoration rule after competition. The resulting system retains the original SAM~3 tracking pipeline while improving target identity preservation in challenging videos. Our submission achieves 66.20 on the primary challenge score and ranks 2nd in the MOSEv2 track.

发表机构

• School of Computer Science, University of Sheffield（谢菲尔德大学计算机学院）
• Department of Automation, Tsinghua University（清华大学自动化系）

机构由 AI 辅助整理，请以论文原文为准。