解决无监督视频目标分割中对象误检与时间不一致问题
FTIO: Frequent Temporally Integrated Objects
- 基于高频出现的显著物体筛选，提升初始分割准确性
- 三阶段融合修复缺失掩码，有效纠正运动与形变导致的时间不连续
- 适合需要高精度多目标分割的视觉分析任务
在真实场景中预测和跟踪物体是视频目标分割（VOS）的核心挑战。无监督VOS（UVOS）还需解决显著物体初始分割难题，这会影响整体流程并持续引入对象提议不确定性。此外，形变与快速运动会导致时间不一致性。为此，我们提出频次时间整合对象（FTIO），一个包含两个关键组件的后处理框架：首先，引入组合准则以改进对象选择，通过提取频繁出现的显著物体，缓解小尺寸或结构复杂物体在UVOS中的常见失败；其次，提出三阶段方法，通过整合缺失的物体掩码区域来修正时间不一致性。实验表明，FTIO在多对象无监督VOS上达到当前最优性能。代码已开源：https://github.com/MohammadMohammadzadehKalati/FTIO
原文摘要 · Abstract (English)
Predicting and tracking objects in real-world scenarios is a critical challenge in Video Object Segmentation (VOS) tasks. Unsupervised VOS (UVOS) has the additional challenge of finding an initial segmentation of salient objects, which affects the entire process and keeps a permanent uncertainty about the object proposals. Moreover, deformation and fast motion can lead to temporal inconsistencies. To address these problems, we propose Frequent Temporally Integrated Objects (FTIO), a post-processing framework with two key components. First, we introduce a combined criterion to improve object selection, mitigating failures common in UVOS--particularly when objects are small or structurally complex--by extracting frequently appearing salient objects. Second, we present a three-stage method to correct temporal inconsistencies by integrating missing object mask regions. Experimental results demonstrate that FTIO achieves state-of-the-art performance in multi-object UVOS. Code is available at: https://github.com/MohammadMohammadzadehKalati/FTIO
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。