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 2312.06592cs.CV
收藏

面向计算机视觉中上下文内学习的灵活视觉提示

Flexible visual prompts for in-context learning in computer vision

V7 Labs(V7实验室)

Thomas Foster, Ioana Croitoru, Robert Dorfman, Christoffer Edlund, Thomas Varsavsky, Jon Almazán

AI总结:

本文将现代VOS技术适配到图像分割ICL,并提出支持集选择方法,在多种数据集和支持集规模下持续优于现有技术,尤其提升未知类别泛化能力。

摘要:

在本工作中,我们处理图像分割任务的上下文内学习(ICL),提出了一种新颖方法,将现代视频对象分割(VOS)技术适配用于视觉上下文内学习。这一适配的灵感来自VOS方法从少量示例中高效且灵活地学习对象的能力。通过在一系列支持集规模以及多种不同分割数据集上进行评估,我们的方法始终优于现有技术。值得注意的是,它在包含训练期间未见过类别的数据上表现出色。此外,我们提出了一种支持集选择技术,即选择最相关的图像纳入该集合。通过采用支持集选择,所有被测试方法的性能都得到提升,而无需额外训练或提示调优。代码可在https://github.com/v7labs/XMem_ICL/获取。

英文摘要:

In this work, we address in-context learning (ICL) for the task of image segmentation, introducing a novel approach that adapts a modern Video Object Segmentation (VOS) technique for visual in-context learning. This adaptation is inspired by the VOS method's ability to efficiently and flexibly learn objects from a few examples. Through evaluations across a range of support set sizes and on diverse segmentation datasets, our method consistently surpasses existing techniques. Notably, it excels with data containing classes not encountered during training. Additionally, we propose a technique for support set selection, which involves choosing the most relevant images to include in this set. By employing support set selection, the performance increases for all tested methods without the need for additional training or prompt tuning. The code can be found at https://github.com/v7labs/XMem_ICL/.

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。

↑