Abstract
Salient object detection (SOD) aims to segment visually prominent regions in images and serves as a foundational task for various computer vision applications. We posit that SOD can now reach near-supervised accuracy without a single pixel-level label, but only when reliable pseudo-masks are available. We revisit the prototype-based line of work and make two key observations. First, boundary pixels and interior pixels obey markedly different geometry; second, the global consistency enforced by optimal transport (OT) is underutilized if prototype quality is weak. To address this, we introduce POTNet, an adaptation of Prototypical Optimal Transport that replaces POT's single k-means step with an entropy-guided dual-clustering head: high-entropy pixels are organized by spectral clustering, low-entropy pixels by k-means, and the two prototype sets are subsequently aligned by OT. This split-fuse-transport design yields sharper, part-aware pseudo-masks in a single forward pass, without handcrafted priors. Those masks supervise a standard MaskFormer-style encoder-decoder, giving rise to AutoSOD, an end-to-end unsupervised SOD pipeline that eliminates SelfMask's offline voting yet improves both accuracy and training efficiency. Extensive experiments on five benchmarks show that AutoSOD outperforms unsupervised methods by up to 26% and weakly supervised methods by up to 36% in F-measure, further narrowing the gap to fully supervised models.
Abstract (translated)
显著对象检测（SOD）旨在分割图像中视觉上突出的区域，并作为各种计算机视觉应用的基础任务。我们提出，现在可以通过利用可靠的伪掩码而不需要单个像素级别的标签来实现接近监督精度的SOD。我们重新审视基于原型的工作，并提出了两个关键观察结果：第一，边界像素和内部像素遵循截然不同的几何特性；第二，在原型质量较弱的情况下，最优传输（OT）所强制执行的整体一致性被低估了。 为了应对这一挑战，我们引入了POTNet，这是对基于原型的最优传输方法的一个改进版本。在新的设计中，我们将POT中的单一k-means步骤替换为由熵引导的双聚类头：高熵像素通过谱聚类组织，低熵像素则通过k-means进行处理，然后使用OT将两个原型集对齐。这种分而治之的设计在一个前向传递过程中产生了更加清晰、具备局部感知能力的伪掩码，并且没有采用手工设计的先验知识。 这些掩码监督了一个标准的MaskFormer风格的编码器-解码器模型，从而诞生了AutoSOD——一种端到端无监督SOD流水线。与SelfMask的离线投票相比，它不仅提高了精度和训练效率，而且还消除了这种依赖性。广泛的实验证明，在五个基准测试上，AutoSOD在F-measure指标上分别比无监督方法高出26%，比弱监督方法高出36%，从而进一步缩小了与完全监督模型之间的差距。
URL
https://arxiv.org/abs/2510.17484
