Unsupervised foreground-background segmentation aims at extracting salient objects from cluttered backgrounds, where Generative Adversarial Network (GAN) approaches, especially layered GANs, show great promise. However, without human annotations, they are typically prone to produce foreground and background layers with non-negligible semantic and visual confusion, dubbed "information leakage", resulting in notable degeneration of the generated segmentation mask. To alleviate this issue, we propose a simple-yet-effective explicit layer independence modeling approach, termed Independent Layer Synthesis GAN (ILSGAN), pursuing independent foreground-background layer generation by encouraging their discrepancy. Specifically, it targets minimizing the mutual information between visible and invisible regions of the foreground and background to spur interlayer independence. Through in-depth theoretical and experimental analyses, we justify that explicit layer independence modeling is critical to suppressing information leakage and contributes to impressive segmentation performance gains. Also, our ILSGAN achieves strong state-of-the-art generation quality and segmentation performance on complex real-world data.

翻译：无监督前景-背景分割旨在从杂乱背景中提取显著目标，其中生成对抗网络（GAN）方法，尤其是分层GAN，展现出巨大潜力。然而，缺乏人工标注时，此类方法常易产生前景与背景层之间存在不可忽视的语义和视觉混淆（即“信息泄露”），导致生成分割掩码显著退化。为解决此问题，我们提出一种简单而有效的显式层独立性建模方法，称为独立层合成GAN（ILSGAN），通过鼓励前景与背景层间的差异，追求独立的层生成。具体而言，它旨在最小化前景与背景中可见与不可见区域间的互信息，以促进层间独立性。通过深入的理论与实验分析，我们论证了显式层独立性建模对抑制信息泄露至关重要，并能显著提升分割性能。此外，我们的ILSGAN在复杂的真实数据上实现了强鲁棒的当前最优生成质量与分割性能。