One key bottleneck of employing state-of-the-art semantic segmentation networks in the real world is the availability of training labels. Conventional semantic segmentation networks require massive pixel-wise annotated labels to reach state-of-the-art prediction quality. Hence, several works focus on semantic segmentation networks trained with only image-level annotations. However, when scrutinizing the results of state-of-the-art in more detail, we notice that they are remarkably close to each other on average prediction quality, different approaches perform better in different classes while providing low quality in others. To address this problem, we propose a novel framework, ISLE, which employs an ensemble of the "pseudo-labels" for a given set of different semantic segmentation techniques on a class-wise level. Pseudo-labels are the pixel-wise predictions of the image-level semantic segmentation frameworks used to train the final segmentation model. Our pseudo-labels seamlessly combine the strong points of multiple segmentation techniques approaches to reach superior prediction quality. We reach up to 2.4% improvement over ISLE's individual components. An exhaustive analysis was performed to demonstrate ISLE's effectiveness over state-of-the-art frameworks for image-level semantic segmentation.

翻译：在现实场景中部署最先进的语义分割网络的关键瓶颈之一是训练标签的可获取性。传统的语义分割网络需要大量像素级标注标签才能达到最先进的预测质量。因此，多项研究聚焦于仅使用图像级标注训练语义分割网络。然而，当更详细地审视最先进方法的结果时，我们发现它们在平均预测质量上非常接近，但不同方法在某些类别上表现更好，而在其他类别上质量较低。为解决这一问题，我们提出了一种新颖框架ISLE，该框架在类别层面上对给定的一组不同语义分割技术的“伪标签”进行集成。伪标签是用于训练最终分割模型的图像级语义分割框架的像素级预测。我们的伪标签无缝融合了多种分割技术方法的优势，从而实现更优的预测质量。与ISLE的各个独立组件相比，我们实现了高达2.4%的提升。通过详尽的分析，我们证明了ISLE在图像级语义分割框架中相较于最先进方法的有效性。