Modeling spatial relationship in the data remains critical across many different tasks, such as image classification, semantic segmentation and protein structure understanding. Previous works often use a unified solution like relative positional encoding. However, there exists different kinds of spatial relations, including short-range, medium-range and long-range relations, and modeling them separately can better capture the focus of different tasks on the multi-range relations (e.g., short-range relations can be important in instance segmentation, while long-range relations should be upweighted for semantic segmentation). In this work, we introduce the EurNet for Efficient multi-range relational modeling. EurNet constructs the multi-relational graph, where each type of edge corresponds to short-, medium- or long-range spatial interactions. In the constructed graph, EurNet adopts a novel modeling layer, called gated relational message passing (GRMP), to propagate multi-relational information across the data. GRMP captures multiple relations within the data with little extra computational cost. We study EurNets in two important domains for image and protein structure modeling. Extensive experiments on ImageNet classification, COCO object detection and ADE20K semantic segmentation verify the gains of EurNet over the previous SoTA FocalNet. On the EC and GO protein function prediction benchmarks, EurNet consistently surpasses the previous SoTA GearNet. Our results demonstrate the strength of EurNets on modeling spatial multi-relational data from various domains. The implementations of EurNet for image modeling are available at https://github.com/hirl-team/EurNet-Image . The implementations for other applied domains/tasks will be released soon.
翻译：模拟数据中的空间关系在许多不同任务中仍然至关重要,例如图像分类、语义网络分割和蛋白结构理解。先前的工作经常使用类似相对位置编码等统一解决方案。然而,存在不同类型的空间关系,包括短程、中程和长程关系,并且分别建模这些关系可以更好地捕捉多种关系任务的重点(例如,短程关系在分解中很重要,而长程关系在语义网络分解中则应该加分。在这项工作中,我们引入了高效多程关系模型模型的 EurNet。EurNet 构建了多关系图,其中每种类型的边缘都与短程、中程和长程空间关系相匹配。在构造图中,EurNet采用一个新的模型,称为关连信息传递(GRMP),以在数据中传播多种关系。GRMP在数据中捕获多种关系,其计算成本很少。我们从两个重要区域研究EurNet 的EurNet,用于图像和蛋白度ERTA 图像和电路路段结构测试。关于我们以往的图像和电路路段数据分析结果的模型测试,将进行关于我们以往的CRM-GMP-O-al-al-al-comal-al-al-al-al-al-al-al-al-al-al-al-al-al-al-al-al-al-al-comal-al-commas的实验, laisalisal laisal laisal laisalisalisal laisal laisalisalation lavicalation laisalment lad ladald lad lad lad lad lad lax sal sal lad lad ladal lad labal lad lad lad lad lad lad lad lad lad lad ladaldal lad ladal lad lad lad lad lad lad lad lad lad lad lad lad lad lad lad lad lad lad lad lad
相关内容
微信扫码咨询专知VIP会员