论文标题
LAPFORMER：轻质准确的息肉分割变压器
LAPFormer: A Light and Accurate Polyp Segmentation Transformer
论文作者
论文摘要
由于各种息肉形状，扫描和标记方式，息肉分割仍然被称为困难问题。这样可以防止深度学习模型在看不见的数据上很好地概括。但是，基于变压器的方法最近在性能方面取得了一些显着的结果，比基于CNN的体系结构更好地提取全球环境的能力，但可以更好地概括。为了利用变压器的强度，我们提出了一个名为Lapformer的编码器架构的新模型，该模型使用层次变压器编码器来更好地提取全局特征，并与我们的新颖CNN（卷积神经网络）解码器结合使用，以捕获息肉的局部外观。我们提出的解码器包含一个渐进式特征融合模块，旨在从上尺和下尺度融合功能，并使多尺度特征更相关。此外，我们还将功能改进模块和功能选择模块用于处理功能。我们在五个流行的基准数据集上测试了我们的模型，以进行息肉细分，包括Kvasir，CVC-Clinic DB，CVC-ColondB，CVC-T和Etis-Larib
Polyp segmentation is still known as a difficult problem due to the large variety of polyp shapes, scanning and labeling modalities. This prevents deep learning model to generalize well on unseen data. However, Transformer-based approach recently has achieved some remarkable results on performance with the ability of extracting global context better than CNN-based architecture and yet lead to better generalization. To leverage this strength of Transformer, we propose a new model with encoder-decoder architecture named LAPFormer, which uses a hierarchical Transformer encoder to better extract global feature and combine with our novel CNN (Convolutional Neural Network) decoder for capturing local appearance of the polyps. Our proposed decoder contains a progressive feature fusion module designed for fusing feature from upper scales and lower scales and enable multi-scale features to be more correlative. Besides, we also use feature refinement module and feature selection module for processing feature. We test our model on five popular benchmark datasets for polyp segmentation, including Kvasir, CVC-Clinic DB, CVC-ColonDB, CVC-T, and ETIS-Larib
