arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.11266eess.IV
收藏

用于无监督图像分割的动态加权损失函数

A Dynamically Weighted Loss Function for Unsupervised Image Segmentation

Boujemaa Guermazi, Riadh Ksantini, Naimul Khan

AI总结:

针对无监督图像分割中固定权重需手动调整的问题,提出动态加权方案,自动平衡特征相似性与空间连续性,在四个数据集上超越现有方法。

摘要:

图像分割是若干计算机视觉任务的基础,其中像素级知识是实现预期目标的前提。深度学习在监督图像分割中已展现出良好的性能。然而,监督分割算法需要大量像素级标注的数据,从而限制了其适用性和可扩展性。因此,有必要投入无监督学习用于分割。本工作提出了一种改进版的无监督卷积神经网络(CNN)算法,该算法使用恒定权重因子来平衡特征相似性与空间连续性这两个分割准则,并且需要根据图像细节程度和数据集持续手动调整参数。相比之下,我们提出了一种新颖的动态加权方案,该方案能够灵活更新参数,并自动调整上述两个准则之间的平衡权重,从而以真正无监督的方式凸显图像中的细节。我们在四个数据集上展示了定量和定性结果,结果表明所提方案在无需手动调整的情况下优于当前的无监督分割方法。

英文摘要:

Image segmentation is the foundation of several computer vision tasks, where pixel-wise knowledge is a prerequisite for achieving the desired target. Deep learning has shown promising performance in supervised image segmentation. However, supervised segmentation algorithms require a massive amount of data annotated at a pixel level, thus limiting their applicability and scalability. Therefore, there is a need to invest in unsupervised learning for segmentation. This work presents an improved version of an unsupervised Convolutional Neural Network (CNN) based algorithm that uses a constant weight factor to balance between the segmentation criteria of feature similarity and spatial continuity, and it requires continuous manual adjustment of parameters depending on the degree of detail in the image and the dataset. In contrast, we propose a novel dynamic weighting scheme that leads to a flexible update of the parameters and an automatic tuning of the balancing weight between the two criteria above to bring out the details in the images in a genuinely unsupervised manner. We present quantitative and qualitative results on four datasets, which show that the proposed scheme outperforms the current unsupervised segmentation approaches without requiring manual adjustment.

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。

↑