arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.11900cs.CV
收藏

SLRNet:通过标签重用对人体分解图像进行半监督式语义分割

SLRNet: Semi-Supervised Semantic Segmentation Via Label Reuse for Human Decomposition Images

The University of Tennessee Knoxville(田纳西大学诺克斯维尔分校)

Sara Mousavi, Zhenning Yang, Kelley Cross, Dawnie Steadman, Audris Mockus

摘要:

语义分割是一项具有挑战性的计算机视觉任务,需要大量的像素级注释数据。产生这些数据是一个耗时且昂贵的过程,特别是对于缺乏专家的领域,如医学或法医人类学。虽然已经开发了许多半监督方法来充分利用有限的标记数据和大量的未标记数据,但特定领域的真实世界数据集通常具有降低现成的最先进方法的有效性的特征,并且还提供了创建利用这些特征的新方法的机会。我们提出并评估了一种半监督方法,该方法通过利用现有的相似性来重用数据集的未标记图像的可用标签,同时在训练过程中动态加权这些重用标签的影响。我们评估了我们的方法在一个大型的人类分解图像数据集,发现我们的方法,而概念上简单,优于最先进的一致性和伪标记为基础的方法分割这个数据集。本文包括人体分解的图形内容。

英文摘要:

Semantic segmentation is a challenging computer vision task demanding a significant amount of pixel-level annotated data. Producing such data is a time-consuming and costly process, especially for domains with a scarcity of experts, such as medicine or forensic anthropology. While numerous semi-supervised approaches have been developed to make the most from the limited labeled data and ample amount of unlabeled data, domain-specific real-world datasets often have characteristics that both reduce the effectiveness of off-the-shelf state-of-the-art methods and also provide opportunities to create new methods that exploit these characteristics. We propose and evaluate a semi-supervised method that reuses available labels for unlabeled images of a dataset by exploiting existing similarities, while dynamically weighting the impact of these reused labels in the training process. We evaluate our method on a large dataset of human decomposition images and find that our method, while conceptually simple, outperforms state-of-the-art consistency and pseudo-labeling-based methods for the segmentation of this dataset. This paper includes graphic content of human decomposition.

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。

↑