用图像掩码重构来解决弱监督分割，隐式融合正则化。
Semantic Segmentation from Image Labels by Reconstruction from Structured Decomposition
- 将弱监督分割建模为基于掩码的图像重构问题。
- 在多个数据集上实现优于主流方法的性能。
- 对背景模糊问题更鲁棒，适合标注稀疏场景。
从图像标签进行弱监督图像分割（WSSS）仍具挑战性，因其约束不足。主流方法多聚焦于提取类别激活图（CAM）并施加多种额外正则化。与主流方法不同，本文提出将 WSSS 视为利用图像掩码进行结构分解重构的问题，使多数正则化项在新问题框架内被隐式嵌入。初步实验表明该方法效果良好，且对背景模糊问题具有更强鲁棒性。代码已开源。
原文摘要 · Abstract (English)
Weakly supervised image segmentation (WSSS) from image tags remains challenging due to its under-constraint nature. Most mainstream work focus on the extraction of class activation map (CAM) and imposing various additional regularization. Contrary to the mainstream, we propose to frame WSSS as a problem of reconstruction from decomposition of the image using its mask, under which most regularization are embedded implicitly within the framework of the new problem. Our approach has demonstrated promising results on initial experiments, and shown robustness against the problem of background ambiguity. Our code is available at \url{https://github.com/xuanrui-work/WSSSByRec}.
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。