Weakly-supervised semantic segmentation (WSSS) is introduced to narrow the gap for semantic segmentation performance from pixel-level supervision to image-level supervision. Most advanced approaches are based on class activation maps (CAMs) to generate pseudo-labels to train the segmentation network. The main limitation of WSSS is that the process of generating pseudo-labels from CAMs that use an image classifier is mainly focused on the most discriminative parts of the objects. To address this issue, we propose Puzzle-CAM, a process that minimizes differences between the features from separate patches and the whole image. Our method consists of a puzzle module and two regularization terms to discover the most integrated region in an object. Puzzle-CAM can activate the overall region of an object using image-level supervision without requiring extra parameters. % In experiments, Puzzle-CAM outperformed previous state-of-the-art methods using the same labels for supervision on the PASCAL VOC 2012 test dataset. In experiments, Puzzle-CAM outperformed previous state-of-the-art methods using the same labels for supervision on the PASCAL VOC 2012 dataset. Code associated with our experiments is available at \url{https://github.com/OFRIN/PuzzleCAM}.

翻译：为缩小语义分解性能的差距,从像素级监督到图像级监督。 大多数高级方法都基于类动图( CAMs) 生成假标签来训练分解网络。 WSSS的主要限制是, 使用图像分类器从 CAMs 生成伪标签的过程主要侧重于对象中最具歧视性的部分。 为了解决这个问题, 我们提议了 拼图- CAM, 这一过程可以将不同补丁和整个图像的特性之间的差异最小化。 我们的方法包括一个解谜模块和两个正规化术语, 以在对象中发现最一体化的区域。 拼图- CAM 可以在不需要额外参数的情况下使用图像级监督器来激活对象的整体区域。% 在实验中, 拼图- CAM 超越了以往使用相同标签来监督 PASALVOC 2012 测试数据集的状态方法。 在实验中, Plock- CAM 超越了先前的状态/ ATRVARCU 。 在2012 可用的 PASAL 数据库中, 使用相同的 PASARCL 。