在扩充曲线目标分割数据集时丰富信息并保持语义一致性
Enriching Information and Preserving Semantic Consistency in Expanding Curvilinear Object Segmentation Datasets
AI总结：
针对曲线目标分割数据集规模小的问题，本文提出结合多文本特征生成数据的扩充方法，构建COSTG数据集，并设计SCP ControlNet保障语义一致性，在多类目标和数据集上验证了能有效提升分割模型性能。
摘要：
曲线目标分割在各类应用中发挥着关键作用，但由于数据采集和标注成本高昂，该领域的数据集通常规模较小。为应对这些挑战，本文提出了一种扩充曲线目标分割数据集的新方法，重点在于提升生成数据的信息量，以及增强语义图与生成图像之间的一致性。\n我们的方法通过利用曲线目标的多种文本特征生成目标，来丰富合成数据的信息量。通过结合原始数据集中每个样本的文本特征，我们得到了超出原始数据集分布的合成图像。这一工作促使我们创建了基于文本生成的曲线目标分割（Curvilinear Object Segmentation based on Text Generation，COSTG）数据集。COSTG旨在突破传统数据集的局限，不仅包含标准语义图，还纳入了部分曲线目标特征的文本描述。\n为确保合成语义图与图像之间的一致性，我们提出了语义一致性保持ControlNet（Semantic Consistency Preserving ControlNet，SCP ControlNet）。该方法对ControlNet进行了适配，引入了空间自适应归一化（Spatially-Adaptive Normalization，SPADE），使其能够保留通常会在归一化层中流失的语义信息。这一改进有助于实现更精准的语义图像合成。\n实验结果在三类曲线目标（血管造影、裂缝和视网膜）及六个公开数据集（CHUAC、XCAD、DCA1、DRIVE、CHASEDB1和Crack500）上验证了我们方法的有效性。我们的方法生成的合成数据不仅扩充了数据集，还有效提升了其他曲线目标分割模型的性能。源代码和数据集可在https://github.com/tanlei0/COSTG获取。
英文摘要：
Curvilinear object segmentation plays a crucial role across various applications, yet datasets in this domain often suffer from small scale due to the high costs associated with data acquisition and annotation. To address these challenges, this paper introduces a novel approach for expanding curvilinear object segmentation datasets, focusing on enhancing the informativeness of generated data and the consistency between semantic maps and generated images. Our method enriches synthetic data informativeness by generating curvilinear objects through their multiple textual features. By combining textual features from each sample in original dataset, we obtain synthetic images that beyond the original dataset's distribution. This initiative necessitated the creation of the Curvilinear Object Segmentation based on Text Generation (COSTG) dataset. Designed to surpass the limitations of conventional datasets, COSTG incorporates not only standard semantic maps but also some textual descriptions of curvilinear object features. To ensure consistency between synthetic semantic maps and images, we introduce the Semantic Consistency Preserving ControlNet (SCP ControlNet). This involves an adaptation of ControlNet with Spatially-Adaptive Normalization (SPADE), allowing it to preserve semantic information that would typically be washed away in normalization layers. This modification facilitates more accurate semantic image synthesis. Experimental results demonstrate the efficacy of our approach across three types of curvilinear objects (angiography, crack and retina) and six public datasets (CHUAC, XCAD, DCA1, DRIVE, CHASEDB1 and Crack500). The synthetic data generated by our method not only expand the dataset, but also effectively improves the performance of other curvilinear object segmentation models. Source code and dataset are available at \url{https://github.com/tanlei0/COSTG}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
