Competitive Memory Readout for Robust Video Object Segmentation: 2nd Place Technical Report for the MOSEv2 Track of the 8th LSVOS Challenge

2026-08-22

AI Summary

本文针对复杂时间动态下的视频对象分割问题，提出了一种竞争性记忆读取方法，以提高目标身份保持的准确性。

Abstract

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.

Problem

• video object segmentation
• temporal dynamics
• long-term occlusion
• appearance changes
• visual interference

Innovation

• Competitive Memory Readout
• adaptive restoration rule
• target identity preservation