arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.04885cs.CV
收藏

VISAGE: 基于外观引导增强的视频实例分割

VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement

Yonsei University(延世大学);Carnegie Mellon University(卡内基梅隆大学);Adobe Research(奥多比研究院)

Hanjung Kim, Jaehyun Kang, Miran Heo, Sukjun Hwang, Seoung Wug Oh, Seon Joo Kim

AI总结:

针对在线视频实例分割方法过度依赖位置信息导致物体关联错误的问题,提出外观引导的解码器扩展方案,同时构建合成数据集验证,最终在多个基准上取得SOTA结果。

摘要:

近年来,在线视频实例分割(VIS)方法凭借其强大的基于查询的检测器取得了显著进展。这类方法利用检测器在帧级输出的查询,在具有挑战性的基准测试上实现了高精度。然而,我们的观察表明,这些方法严重依赖位置信息,这往往会导致物体之间的关联错误。本文提出,跟踪器中物体匹配的一个核心维度是外观信息,在位置线索不足以区分物体身份的情况下,外观信息会极具指导意义。因此,我们提出了一种简单但功能强大的物体解码器扩展方案,该方案能从骨干网络特征中显式提取嵌入向量,并驱动查询捕捉物体的外观,从而大幅提升实例关联的准确性。此外,我们认识到现有基准在全面评估外观感知能力方面存在局限性,因此构建了一个合成数据集以严格验证我们的方法。通过有效解决对位置信息的过度依赖问题,我们在YouTube-VIS 2019/2021和Occluded VIS(OVIS)数据集上取得了当前最优的结果。代码可在https://github.com/KimHanjung/VISAGE获取。

英文摘要:

In recent years, online Video Instance Segmentation (VIS) methods have shown remarkable advancement with their powerful query-based detectors. Utilizing the output queries of the detector at the frame-level, these methods achieve high accuracy on challenging benchmarks. However, our observations demonstrate that these methods heavily rely on location information, which often causes incorrect associations between objects. This paper presents that a key axis of object matching in trackers is appearance information, which becomes greatly instructive under conditions where positional cues are insufficient for distinguishing their identities. Therefore, we suggest a simple yet powerful extension to object decoders that explicitly extract embeddings from backbone features and drive queries to capture the appearances of objects, which greatly enhances instance association accuracy. Furthermore, recognizing the limitations of existing benchmarks in fully evaluating appearance awareness, we have constructed a synthetic dataset to rigorously validate our method. By effectively resolving the over-reliance on location information, we achieve state-of-the-art results on YouTube-VIS 2019/2021 and Occluded VIS (OVIS). Code is available at https://github.com/KimHanjung/VISAGE.

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。

↑