论文标题
弱监督语义细分的阶层间和阶层间关系约束
Saliency Guided Inter- and Intra-Class Relation Constraints for Weakly Supervised Semantic Segmentation
论文作者
论文摘要
仅使用图像级标签的弱监督语义细分旨在降低分段任务的注释成本。现有方法通常利用类激活图（CAM）定位伪标签的对象区域。但是，凸轮只能发现对象的最歧视部分，从而导致较低的像素级伪标签。为了解决这个问题，我们提出了一个限制的显着性和内类关系（I $^2 $ CRC）框架，以协助CAM中激活的对象区域的扩展。具体而言，我们提出了一个显着性指导的类别不稳定的距离模块，以通过将特征与其类原型对齐来更接近类别内特征。此外，我们提出了一个特定的距离模块，以将类间特征推开，并鼓励对象区域的激活高于背景。除了增强分类网络激活CAM中更多积分对象区域的能力外，我们还引入了一个对象引导的标签改进模块，以完全使用分段预测和初始标签，以获得出色的伪标签。 Pascal VOC 2012和可可数据集的广泛实验很好地证明了I $^2 $ CRC的有效性，而不是其他最先进的对应物。源代码，模型和数据已在\ url {https://github.com/nust-machine-intelligence-laboratory/i2crc}提供。
Weakly supervised semantic segmentation with only image-level labels aims to reduce annotation costs for the segmentation task. Existing approaches generally leverage class activation maps (CAMs) to locate the object regions for pseudo label generation. However, CAMs can only discover the most discriminative parts of objects, thus leading to inferior pixel-level pseudo labels. To address this issue, we propose a saliency guided Inter- and Intra-Class Relation Constrained (I$^2$CRC) framework to assist the expansion of the activated object regions in CAMs. Specifically, we propose a saliency guided class-agnostic distance module to pull the intra-category features closer by aligning features to their class prototypes. Further, we propose a class-specific distance module to push the inter-class features apart and encourage the object region to have a higher activation than the background. Besides strengthening the capability of the classification network to activate more integral object regions in CAMs, we also introduce an object guided label refinement module to take a full use of both the segmentation prediction and the initial labels for obtaining superior pseudo-labels. Extensive experiments on PASCAL VOC 2012 and COCO datasets demonstrate well the effectiveness of I$^2$CRC over other state-of-the-art counterparts. The source codes, models, and data have been made available at \url{https://github.com/NUST-Machine-Intelligence-Laboratory/I2CRC}.
