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 2401.10044cs.CV
收藏

Deep spatial context:当基于注意力的模型遇到空间回归

Deep spatial context: when attention-based models meet spatial regression

Faculty of Mathematics and Information Science(数学与信息科学学院);Warsaw University of Technology(华沙理工大学);Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院)

Paulina Tomaszewska, Elżbieta Sienkiewicz, Mai P. Hoang, Przemysław Biecek

AI总结:

本研究提出DSCon深度空间上下文方法,整合空间回归与三类度量量化分析注意力视觉模型的空间上下文作用,经实验揭示了肿瘤/正常组织分类、邻域大小、不同空间下的空间上下文规律。

摘要:

我们提出了Deep spatial context(DSCon,深度空间上下文)方法,该方法借助空间上下文概念用于研究基于注意力的视觉模型。其灵感来自组织病理学家,但该方法可应用于多个领域。DSCon通过三个空间上下文度量(Spatial Context Measures):$SCM_{features}$、$SCM_{targets}$、$SCM_{residuals}$,实现对空间上下文作用的量化衡量,分别用于区分空间上下文是否可在相邻区域的特征、其目标值(注意力分数)或残差中被观测到。这一方法通过将空间回归整合到流程中实现,可用于验证各类研究问题。实验显示,在肿瘤病变分类场景下,空间关系的作用远大于正常组织分类场景;此外,空间回归中考虑的邻域尺寸越大,上下文信息的价值越低;另外还观测到,与目标空间和残差空间相比,在特征空间中计算得到的空间上下文度量值最大。

英文摘要:

We propose 'Deep spatial context' (DSCon) method, which serves for investigation of the attention-based vision models using the concept of spatial context. It was inspired by histopathologists, however, the method can be applied to various domains. The DSCon allows for a quantitative measure of the spatial context's role using three Spatial Context Measures: $SCM_{features}$, $SCM_{targets}$, $SCM_{residuals}$ to distinguish whether the spatial context is observable within the features of neighboring regions, their target values (attention scores) or residuals, respectively. It is achieved by integrating spatial regression into the pipeline. The DSCon helps to verify research questions. The experiments reveal that spatial relationships are much bigger in the case of the classification of tumor lesions than normal tissues. Moreover, it turns out that the larger the size of the neighborhood taken into account within spatial regression, the less valuable contextual information is. Furthermore, it is observed that the spatial context measure is the largest when considered within the feature space as opposed to the targets and residuals.

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。

↑