arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.01872cs.CV
收藏

MOSE:面向复杂场景视频目标分割的新数据集

MOSE: A New Dataset for Video Object Segmentation in Complex Scenes

Nanyang Technological University(南洋理工大学);Zhejiang University(浙江大学);University of Oxford(牛津大学);ByteDance(字节跳动)

Henghui Ding, Chang Liu, Shuting He, Xudong Jiang, Philip H. S. Torr, Song Bai

AI总结:

针对复杂场景下视频目标分割研究不足的问题,本文提出了包含拥挤和遮挡目标的新数据集MOSE,通过对18种现有VOS方法的基准测试揭示了当前算法在复杂场景下的性能瓶颈与未来挑战。

摘要:

视频目标分割(VOS)旨在整个视频片段序列中分割特定目标。现有最先进的VOS方法在现有数据集上取得了优异的性能(例如,90+% J&F)。然而,由于这些现有数据集中的目标通常相对显著、主导且孤立,复杂场景下的VOS很少被研究。为了重新审视VOS并使其在现实世界中更具适用性,我们收集了一个名为coMplex video Object SEgmentation(MOSE)的新VOS数据集,以研究复杂环境中的目标跟踪与分割。MOSE包含来自36个类别的2,149个视频片段和5,200个目标,以及431,725个高质量目标分割掩码。MOSE数据集最显著的特征是包含拥挤和被遮挡目标的复杂场景。视频中的目标通常被其他目标遮挡,并在某些帧中消失。为了分析提出的MOSE数据集,我们在该数据集上对18种现有VOS方法在4种不同设置下进行了基准测试,并进行了全面比较。实验表明,当前的VOS算法无法很好地感知复杂场景中的目标。例如,在半监督VOS设置下,现有最先进的VOS方法在MOSE上的最高J&F仅为59.4%,远低于它们在DAVIS上约90%的J&F性能。结果表明,尽管在现有基准上取得了优异性能,但复杂场景下仍存在未解决的挑战,未来需要更多努力来探索这些挑战。提出的MOSE数据集已发布于https://henghuiding.github.io/MOSE。

英文摘要:

Video object segmentation (VOS) aims at segmenting a particular object throughout the entire video clip sequence. The state-of-the-art VOS methods have achieved excellent performance (e.g., 90+% J&F) on existing datasets. However, since the target objects in these existing datasets are usually relatively salient, dominant, and isolated, VOS under complex scenes has rarely been studied. To revisit VOS and make it more applicable in the real world, we collect a new VOS dataset called coMplex video Object SEgmentation (MOSE) to study the tracking and segmenting objects in complex environments. MOSE contains 2,149 video clips and 5,200 objects from 36 categories, with 431,725 high-quality object segmentation masks. The most notable feature of MOSE dataset is complex scenes with crowded and occluded objects. The target objects in the videos are commonly occluded by others and disappear in some frames. To analyze the proposed MOSE dataset, we benchmark 18 existing VOS methods under 4 different settings on the proposed MOSE dataset and conduct comprehensive comparisons. The experiments show that current VOS algorithms cannot well perceive objects in complex scenes. For example, under the semi-supervised VOS setting, the highest J&F by existing state-of-the-art VOS methods is only 59.4% on MOSE, much lower than their ~90% J&F performance on DAVIS. The results reveal that although excellent performance has been achieved on existing benchmarks, there are unresolved challenges under complex scenes and more efforts are desired to explore these challenges in the future. The proposed MOSE dataset has been released at https://henghuiding.github.io/MOSE.

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。

↑