面向端到端弱监督语义分割的分支互促方法
Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation
AI总结：
本文提出一种端到端弱监督语义分割方法，通过双向监督机制和分支间交互操作，使分类分支与分割分支平等互促，从而提升分割性能。
摘要：
端到端弱监督语义分割旨在仅基于图像级标注，通过单阶段训练过程优化分割模型。现有方法采用在线训练的分类分支为分割分支提供伪标注进行监督。然而，这种策略使分类分支主导整个并行训练过程，阻碍了两个分支之间的相互辅助。在我们的工作中，我们将这两个分支平等对待，将其视为生成分割图的不同方式，并在其监督和操作两方面引入交互以实现互促。为此，我们设计了一种双向监督机制，强制两个分支输出之间保持一致。因此，分割分支也可以向分类分支反馈，以提升定位种子（localization seeds）的质量。此外，我们的方法还设计了两个分支之间的交互操作，以交换知识并相互辅助。实验表明，我们的工作优于现有的端到端弱监督分割方法。
英文摘要：
End-to-end weakly supervised semantic segmentation aims at optimizing a segmentation model in a single-stage training process based on only image annotations. Existing methods adopt an online-trained classification branch to provide pseudo annotations for supervising the segmentation branch. However, this strategy makes the classification branch dominate the whole concurrent training process, hindering these two branches from assisting each other. In our work, we treat these two branches equally by viewing them as diverse ways to generate the segmentation map, and add interactions on both their supervision and operation to achieve mutual promotion. For this purpose, a bidirectional supervision mechanism is elaborated to force the consistency between the outputs of these two branches. Thus, the segmentation branch can also give feedback to the classification branch to enhance the quality of localization seeds. Moreover, our method also designs interaction operations between these two branches to exchange their knowledge to assist each other. Experiments indicate our work outperforms existing end-to-end weakly supervised segmentation methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
