Weakly supervised semantic segmentation (WSSS) aims to produce pixel-wise class predictions with only image-level labels for training. To this end, previous methods adopt the common pipeline: they generate pseudo masks from class activation maps (CAMs) and use such masks to supervise segmentation networks. However, it is challenging to derive comprehensive pseudo masks that cover the whole extent of objects due to the local property of CAMs, i.e., they tend to focus solely on small discriminative object parts. In this paper, we associate the locality of CAMs with the texture-biased property of convolutional neural networks (CNNs). Accordingly, we propose to exploit shape information to supplement the texture-biased CNN features, thereby encouraging mask predictions to be not only comprehensive but also well-aligned with object boundaries. We further refine the predictions in an online fashion with a novel refinement method that takes into account both the class and the color affinities, in order to generate reliable pseudo masks to supervise the model. Importantly, our model is end-to-end trained within a single-stage framework and therefore efficient in terms of the training cost. Through extensive experiments on PASCAL VOC 2012, we validate the effectiveness of our method in producing precise and shape-aligned segmentation results. Specifically, our model surpasses the existing state-of-the-art single-stage approaches by large margins. What is more, it also achieves a new state-of-the-art performance over multi-stage approaches, when adopted in a simple two-stage pipeline without bells and whistles.
翻译:微弱监管的语义分解( WSSS) 旨在生成像素类类预测, 仅以图像级标签作为培训标签。 为此, 以往的方法采用共同管道: 以类级激活地图生成假面具, 并使用这种面具来监管分解网络。 然而, 很难获得涵盖因CAM的本地特性而导致的物体范围的全面假面具, 即它们往往只侧重于小的有区别对象部分。 在本文中, 我们将CAM 的位置与相近神经网络( CNNs) 的质端偏属性联系起来。 因此, 我们提议利用图像信息来补充带有纹度的CNN CNN 特征, 从而鼓励假面具的预测不仅全面, 而且与对象界限完全吻合。 我们进一步以在线方式完善预测, 一种考虑到等级和颜色相似性的新改进方法, 以便产生可靠的假面具来监督模型。 极好, 我们的模型是在单一级神经网络网络网络( CNNs) 的纹端到端属性属性属性属性属性属性属性属性属性。 因此, 我们提议利用生成信息来完善信息信息信息, 以一阶段级框架中的大规模的模型, 并且通过常规化常规化常规化的常规化的常规化的常规化, 。