Abstract
Autonomous robotic systems applied to new domains require an abundance of expensive, pixel-level dense labels to train robust semantic segmentation models under full supervision. This study proposes a model-agnostic Depth Edge Alignment Loss to improve Weakly Supervised Semantic Segmentation models across different datasets. The methodology generates pixel-level semantic labels from image-level supervision, avoiding expensive annotation processes. While weak supervision is widely explored in traditional computer vision, our approach adds supervision with pixel-level depth information, a modality commonly available in robotic systems. We demonstrate how our approach improves segmentation performance across datasets and models, but can also be combined with other losses for even better performance, with improvements up to +5.439, +1.274 and +16.416 points in mean Intersection over Union on the PASCAL VOC / MS COCO validation, and the HOPE static onboarding split, respectively. Our code will be made publicly available.
Abstract (translated)
自主机器人系统在新领域的应用需要大量的昂贵的像素级密集标签来训练完全监督下的稳健语义分割模型。本研究提出了一种与模型无关的深度边缘对齐损失（Depth Edge Alignment Loss），以改进跨不同数据集的弱监督语义分割模型。该方法通过图像级别的监督生成像素级语义标签，从而避免了昂贵的标注过程。尽管传统计算机视觉中广泛探索了弱监督问题，但我们的方法增加了像素级深度信息作为监督，这种模态在机器人系统中通常可以获取到。我们展示了如何改进不同数据集和模型上的分割性能，并且该方法还可以与其他损失结合使用以获得更好的效果，在PASCAL VOC / MS COCO验证集和HOPE静态上行分集分别提高了+5.439，+1.274和+16.416的平均交并比（mean Intersection over Union）点数。我们的代码将公开发布。
URL
https://arxiv.org/abs/2509.17702
