arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.23788cs.CV
收藏

通过目标检索重新提示SAM 3:5th PVUW MOSE Track的第三篇

Re-Prompting SAM 3 via Object Retrieval: 3rd of the 5th PVUW MOSE Track

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

Mingqi Gao, Sijie Li, Jungong Han

AI总结:

本文基于SAM 3开发自动重新提示框架,通过目标检索提升视频目标分割的鲁棒性,实现51.17%的J&F成绩,在MOSEv2 Track中排名第三。

摘要:

本技术报告探讨了PVUW 2026挑战中的MOSEv2 track,目标是复杂的半监督视频目标分割。基于SAM 3,我们开发了一个自动重新提示框架,以提高在目标消失和出现、严重变换和强同类干扰下的鲁棒性。我们的方法首先使用SAM 3检测器在后续帧中识别同类对象候选,然后通过基于DINOv3的对象级匹配和具有变换意识的目标特征池进行检索,以获取可靠的靶标锚点。这些锚点与第一帧掩码一起注入到SAM 3跟踪器中,实现多锚点传播,而不是仅依赖初始提示。这种简单直接的方法有助于解决MOSEv2的几个核心挑战。我们的解决方案在测试集上实现了51.17%的J&F,排名MOSEv2 track第三。

英文摘要:

This technical report explores the MOSEv2 track of the PVUW 2026 Challenge, which targets complex semi-supervised video object segmentation. Built on SAM~3, we develop an automatic re-prompting framework to improve robustness under target disappearance and reappearance, severe transformation, and strong same-category distractors. Our method first applies the SAM~3 detector to later frames to identify same-category object candidates, and then performs DINOv3-based object-level matching with a transformation-aware target feature pool to retrieve reliable target anchors. These anchors are injected back into the SAM~3 tracker together with the first-frame mask, enabling multi-anchor propagation rather than relying solely on the initial prompt. This simple directly benefits several core challenges of MOSEv2. Our solution achieves a J&F of 51.17% on the test set, ranking 3rd in the MOSEv2 track.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑