Abstract
As a computer vision task, automatic object segmentation remains challenging in specialized image domains without massive labeled data, such as synthetic aperture sonar images, remote sensing, biomedical imaging, etc. In any domain, obtaining pixel-wise segmentation masks is expensive. In this work, we propose a method for training a masking network to perform binary object segmentation using weak supervision in the form of image-wise presence or absence of an object of interest, which provides less information but may be obtained more quickly from manual or automatic labeling. A key step in our method is that the segmented objects can be placed into background-only images to create realistic, images of the objects with counterfactual backgrounds. To create a contrast between the original and counterfactual background images, we propose to first cluster the background-only images, and then during learning create counterfactual images that blend objects segmented from their original source backgrounds to backgrounds chosen from a targeted cluster. One term in the training loss is the divergence between these counterfactual images and the real object images with backgrounds of the target cluster. The other term is a supervised loss for background-only images. While an adversarial critic could provide the divergence, we use sample-based divergences. We conduct experiments on side-scan and synthetic aperture sonar in which our approach succeeds compared to previous unsupervised segmentation baselines that were only tested on natural images. Furthermore, to show generality we extend our experiments to natural images, obtaining reasonable performance with our method that avoids pretrained networks, generative networks, and adversarial critics. The basecode for this work can be found at \href{GitHub}{this https URL}.
Abstract (translated)
作为计算机视觉任务，自动对象分割在缺乏大规模标注数据的专业图像领域中仍然具有挑战性，例如合成孔径声纳图像、遥感和生物医学成像等。在任何领域中，获取像素级的分割掩模都是昂贵的。在这项工作中，我们提出了一种方法，通过弱监督（以目标对象在图像中的存在与否的形式）来训练遮罩网络进行二元物体分割。这种形式提供的信息较少，但可以从手动或自动标记中更快地获得。 我们方法的关键步骤是将分割出的对象放置到仅包含背景的图片中，创建具有反事实背景的目标对象的真实图像。为了在原始和反事实背景图像之间形成对比，我们首先对仅含背景的图像进行聚类，在学习过程中生成混合来自目标聚类背景中的反事实图像。这些反事实图像是通过将从它们原出处背景分割出来的物体与从特定簇中选取的背景融合而来的。 训练损失的一个项是这些反事实图像与其具有目标群集背景的真实对象图像之间的散度。另一个项则是仅含背景图像的监督损失。尽管对抗性批评者可以提供这种散度，但我们使用基于样本的散度。我们在侧扫声纳和合成孔径声纳上进行了实验，在这些领域中我们的方法优于以往仅在自然图像上测试过的无监督分割基准模型。 为了展示其通用性，我们将实验扩展到自然图像，并且无需预训练网络、生成式网络或对抗性批评者即可获得合理性能。这项工作的基础代码可以在GitHub上的[此链接](https://github.com/your-repo-url-here)找到。
URL
https://arxiv.org/abs/2506.22505
