论文标题
空间独家粘贴：息肉细分的一般数据增强
Spatially Exclusive Pasting: A General Data Augmentation for the Polyp Segmentation
论文作者
论文摘要
自动息肉分割技术在诊断肠道疾病（例如肿瘤和癌前病变）中起着重要作用。先前的工作通常已经训练了带有标记数据的基于卷积的U-NET或基于变压器的神经网络体系结构。但是，可用的公共息肉细分数据集太小了，无法充分训练网络，从而抑制了每个网络的潜在性能。为了减轻此问题，我们提出了一种通用数据增强技术，以综合现有数据集中的更多数据。具体而言，我们以空间排他性的方式将息肉区域粘贴到同一图像的背景中，以获得组合数的新图像。在各种网络和数据集上进行的广泛实验表明，所提出的方法提高了数据效率，并实现了对基准的一致改进。最后，我们在这项任务中达到了新的最新状态。我们将尽快发布代码。
Automated polyp segmentation technology plays an important role in diagnosing intestinal diseases, such as tumors and precancerous lesions. Previous works have typically trained convolution-based U-Net or Transformer-based neural network architectures with labeled data. However, the available public polyp segmentation datasets are too small to train the network sufficiently, suppressing each network's potential performance. To alleviate this issue, we propose a universal data augmentation technology to synthesize more data from the existing datasets. Specifically, we paste the polyp area into the same image's background in a spatial-exclusive manner to obtain a combinatorial number of new images. Extensive experiments on various networks and datasets show that the proposed method enhances the data efficiency and achieves consistent improvements over baselines. Finally, we hit a new state of the art in this task. We will release the code soon.
