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 2409.06305cs.CV
收藏

使用基础模型实现高性能小样本分割:一项实证研究

High-Performance Few-Shot Segmentation with Foundation Models: An Empirical Study

School of Information and Communication Engineering, Dalian University of Technology(大连理工大学信息与通信工程学院);School of Future Technology, Dalian University of Technology(大连理工大学未来技术学院)

Shijie Chang, Lihe Zhang, Huchuan Lu

AI总结:

本文提出基于基础模型的小样本分割框架,通过提取隐式知识构建粗对应并以轻量解码器细化,实证表明DINOv2与DFN组合在COCO-20i上超越此前最优方法17.5%。

摘要:

现有的小样本分割(FSS)方法主要专注于设计新颖的支持-查询匹配和自匹配机制,以利用预训练骨干网络中的隐式知识。然而,这些方法的性能往往受到在分类任务上预训练的模型的限制。关于哪些类型的预训练模型能够为FSS提供更有益隐式知识的探索仍然有限。本文受基础计算机视觉模型的表征一致性启发,开发了一个基于基础模型的FSS框架。具体而言,我们提出了一种从基础模型中提取隐式知识以构建粗对应关系的简单方法,并引入一个轻量级解码器来细化粗对应关系,从而实现细粒度分割。我们系统总结了各种基础模型在FSS上的性能,并发现其中部分模型所含的隐式知识比在分类任务上预训练的模型更有利于FSS。在两个广泛使用的数据集上进行的大量实验证明了本方法在利用基础模型隐式知识方面的有效性。值得注意的是,DINOv2与DFN的组合在COCO-20i上比此前最先进方法高出17.5%。代码位于https://github.com/DUT-CSJ/FoundationFSS。

英文摘要:

Existing few-shot segmentation (FSS) methods mainly focus on designing novel support-query matching and self-matching mechanisms to exploit implicit knowledge in pre-trained backbones. However, the performance of these methods is often constrained by models pre-trained on classification tasks. The exploration of what types of pre-trained models can provide more beneficial implicit knowledge for FSS remains limited. In this paper, inspired by the representation consistency of foundational computer vision models, we develop a FSS framework based on foundation models. To be specific, we propose a simple approach to extract implicit knowledge from foundation models to construct coarse correspondence and introduce a lightweight decoder to refine coarse correspondence for fine-grained segmentation. We systematically summarize the performance of various foundation models on FSS and discover that the implicit knowledge within some of these models is more beneficial for FSS than models pre-trained on classification tasks. Extensive experiments on two widely used datasets demonstrate the effectiveness of our approach in leveraging the implicit knowledge of foundation models. Notably, the combination of DINOv2 and DFN exceeds previous state-of-the-art methods by 17.5% on COCO-20i. Code is available at https://github.com/DUT-CSJ/FoundationFSS.

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。

↑