论文标题
使用层次间的关注来改善变压器中的语义细分
Improving Semantic Segmentation in Transformers using Hierarchical Inter-Level Attention
论文作者
论文摘要
现有的基于变压器的图像骨干通常会从一个方向传播特征信息，从较低到更高级别。这可能不是理想的选择，因为划定准确对象边界的本地化能力，在较低的高分辨率特征图中最突出，而可以放弃属于一个对象的图像信号而不是另一个对象的语义，通常出现在较高的处理中。我们提出了层次层间注意力（HILA），这是一种基于注意力的方法，可在不同级别的功能之间捕获自下而上的更新和自上而下的更新。 Hila通过将较高和较低级别的特征之间的局部连接添加到骨干编码器中，扩展了层次视觉变压器体系结构。在每次迭代中，我们通过具有更高级别的功能来竞争分配来更新属于它们的低级功能，从而构建层次结构，从而迭代解决对象零件关系。然后使用这些改进的低级功能来更新更高级别的功能。 HILA可以集成到大多数层次结构中，而无需对基本模型进行任何更改。我们将HILA添加到Segformer和Swin Transformer中，并以更少的参数和拖鞋的方式显示出显着的语义分割精度。项目网站和代码：https：//www.cs.toronto.edu/~garyleung/hila/
Existing transformer-based image backbones typically propagate feature information in one direction from lower to higher-levels. This may not be ideal since the localization ability to delineate accurate object boundaries, is most prominent in the lower, high-resolution feature maps, while the semantics that can disambiguate image signals belonging to one object vs. another, typically emerges in a higher level of processing. We present Hierarchical Inter-Level Attention (HILA), an attention-based method that captures Bottom-Up and Top-Down Updates between features of different levels. HILA extends hierarchical vision transformer architectures by adding local connections between features of higher and lower levels to the backbone encoder. In each iteration, we construct a hierarchy by having higher-level features compete for assignments to update lower-level features belonging to them, iteratively resolving object-part relationships. These improved lower-level features are then used to re-update the higher-level features. HILA can be integrated into the majority of hierarchical architectures without requiring any changes to the base model. We add HILA into SegFormer and the Swin Transformer and show notable improvements in accuracy in semantic segmentation with fewer parameters and FLOPS. Project website and code: https://www.cs.toronto.edu/~garyleung/hila/
