论文标题
Sasformer：用于稀疏注释语义分段的变压器
SASFormer: Transformers for Sparsely Annotated Semantic Segmentation
论文作者
论文摘要
近年来，基于稀疏注释的语义细分已经提高。它仅标记图像中每个对象的一部分，而其余的未标记。大多数现有的方法都是耗时的，通常需要采取多阶段培训策略。在这项工作中，我们提出了一个简单而有效的稀疏注释的语义分割框架，基于Segformer，称为Sasformer，可实现出色的性能。具体而言，该框架首先生成层次补丁注意图，然后将其乘以网络预测，以产生由有效标签分开的相关区域。此外，我们还引入了亲和力损失，以确保相关结果和网络预测的特征之间的一致性。广泛的实验表明，我们提出的方法优于现有方法，并实现了尖端的性能。源代码可在\ url {https://github.com/su-hui-zz/sasformer}中获得。
Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existing approaches are time-consuming and often necessitate a multi-stage training strategy. In this work, we propose a simple yet effective sparse annotated semantic segmentation framework based on segformer, dubbed SASFormer, that achieves remarkable performance. Specifically, the framework first generates hierarchical patch attention maps, which are then multiplied by the network predictions to produce correlated regions separated by valid labels. Besides, we also introduce the affinity loss to ensure consistency between the features of correlation results and network predictions. Extensive experiments showcase that our proposed approach is superior to existing methods and achieves cutting-edge performance. The source code is available at \url{https://github.com/su-hui-zz/SASFormer}.
