MARIO用多种标注方式训练肠息肉分割模型，降低标注成本。
MARIO: A Mixed Annotation Framework For Polyp Segmentation
- 融合五类标注（像素、框、多边形、草图、点）实现混合监督。
- 在五个基准数据集上均优于现有方法，提升分割性能。
- 主要使用弱标注数据，减少对昂贵全标注数据依赖。
现有肠息肉分割模型受限于高标注成本和数据集规模小，且大量息肉数据因仅支持单一标注类型而未被充分利用。为解决此问题，本文提出MARIO，一种可兼容多种标注形式的混合监督模型。MARIO通过引入五种监督形式——像素级、框级、多边形级、草图级和点级——并为每种设计专用损失函数，有效利用标注信息同时抑制噪声。该方法突破了传统模型对单一标注类型的依赖，主要基于弱标注数据训练，显著降低对大规模全标注数据的依赖。在五个基准数据集上的实验结果表明，MARIO持续优于现有方法，证明其在平衡不同监督形式间权衡、最大化分割性能方面的有效性。
原文摘要 · Abstract (English)
Existing polyp segmentation models are limited by high labeling costs and the small size of datasets. Additionally, vast polyp datasets remain underutilized because these models typically rely on a single type of annotation. To address this dilemma, we introduce MARIO, a mixed supervision model designed to accommodate various annotation types, significantly expanding the range of usable data. MARIO learns from underutilized datasets by incorporating five forms of supervision: pixel-level, box-level, polygon-level, scribblelevel, and point-level. Each form of supervision is associated with a tailored loss that effectively leverages the supervision labels while minimizing the noise. This allows MARIO to move beyond the constraints of relying on a single annotation type. Furthermore, MARIO primarily utilizes dataset with weak and cheap annotations, reducing the dependence on large-scale, fully annotated ones. Experimental results across five benchmark datasets demonstrate that MARIO consistently outperforms existing methods, highlighting its efficacy in balancing trade-offs between different forms of supervision and maximizing polyp segmentation performance
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。