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 2412.12423cs.LG
收藏

GG-SSMs:图生成状态空间模型

GG-SSMs: Graph-Generating State Space Models

University of Zurich(苏黎世大学)

Nikola Zubić, Davide Scaramuzza

AI总结:

提出图生成状态空间模型(GG-SSMs),通过基于特征关系动态构建图并利用最小生成树算法,克服传统SSMs固定序列处理的限制,在11个数据集上实现最先进性能。

摘要:

状态空间模型(SSMs)是计算机视觉和时间序列分析领域中用于建模序列数据的强大工具。然而,传统的SSMs受限于固定的、一维的序列处理方式,这限制了它们对高维数据中非局部交互的建模能力。尽管Mamba和VMamba等方法引入了选择性且灵活的扫描策略,但它们依赖于预定路径,无法有效捕获复杂的依赖关系。我们提出了图生成状态空间模型(GG-SSMs),这是一种新颖的框架,通过基于特征关系动态构建图来克服这些限制。利用Chazelle的最小生成树算法,GG-SSMs能够适应数据的内在结构,从而在动态生成的图上实现稳健的特征传播,并高效建模复杂的依赖关系。我们在11个多样化的数据集上验证了GG-SSMs,包括基于事件的眼动追踪、ImageNet分类、光流估计以及六个时间序列数据集。GG-SSMs在所有任务上均取得了最先进的性能,以显著优势超越了现有方法。具体而言,GG-SSM在ImageNet上实现了84.9%的top-1准确率,比先前的SSMs高出1%,将KITTI-15误差率降至2.77%,并在使用更少参数的情况下将眼动追踪检测率最高提升了0.33%。这些结果表明,基于特征关系的动态扫描显著提升了SSMs的表示能力与效率,为计算机视觉及其他领域的各种应用提供了一种通用工具。

英文摘要:

State Space Models (SSMs) are powerful tools for modeling sequential data in computer vision and time series analysis domains. However, traditional SSMs are limited by fixed, one-dimensional sequential processing, which restricts their ability to model non-local interactions in high-dimensional data. While methods like Mamba and VMamba introduce selective and flexible scanning strategies, they rely on predetermined paths, which fails to efficiently capture complex dependencies. We introduce Graph-Generating State Space Models (GG-SSMs), a novel framework that overcomes these limitations by dynamically constructing graphs based on feature relationships. Using Chazelle's Minimum Spanning Tree algorithm, GG-SSMs adapt to the inherent data structure, enabling robust feature propagation across dynamically generated graphs and efficiently modeling complex dependencies. We validate GG-SSMs on 11 diverse datasets, including event-based eye-tracking, ImageNet classification, optical flow estimation, and six time series datasets. GG-SSMs achieve state-of-the-art performance across all tasks, surpassing existing methods by significant margins. Specifically, GG-SSM attains a top-1 accuracy of 84.9% on ImageNet, outperforming prior SSMs by 1%, reducing the KITTI-15 error rate to 2.77%, and improving eye-tracking detection rates by up to 0.33% with fewer parameters. These results demonstrate that dynamic scanning based on feature relationships significantly improves SSMs' representational power and efficiency, offering a versatile tool for various applications in computer vision and beyond.

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。

↑