用盒子生成像素标签，用标签生成盒子，提升弱监督多任务学习效果
Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning
- 利用盒子标签生成对应像素标签，反向训练分割模型
- 在VOC和COCO上比基线提升1.5~3.2个点，验证有效性
- 适合数据标注不完整但需联合训练的场景
目标检测与语义分割虽同属场景理解任务，但数据结构与信息层级不同：前者需要实例框坐标，后者需要像素级类别标签。若能利用一种任务的信息辅助训练另一种，将有助于多任务弱监督学习——即每个样本仅标注单一任务。本文研究了多种弱监督损失，并提出Box-for-Mask与Mask-for-Box策略及其组合BoMBo，通过从已有任务标注中提炼必要信息，指导另一任务训练。在VOC与COCO数据集上的消融实验与结果表明，该方法显著有效。代码与数据划分见https://github.com/lhoangan/multas。
原文摘要 · Abstract (English)
Object detection and semantic segmentation are both scene understanding tasks yet they differ in data structure and information level. Object detection requires box coordinates for object instances while semantic segmentation requires pixel-wise class labels. Making use of one task's information to train the other would be beneficial for multi-task partially supervised learning where each training example is annotated only for a single task, having the potential to expand training sets with different-task datasets. This paper studies various weak losses for partially annotated data in combination with existing supervised losses. We propose Box-for-Mask and Mask-for-Box strategies, and their combination BoMBo, to distil necessary information from one task annotations to train the other. Ablation studies and experimental results on VOC and COCO datasets show favorable results for the proposed idea. Source code and data splits can be found at https://github.com/lhoangan/multas.
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。