论文标题
弱监督语义分割的因果干预
Causal Intervention for Weakly-Supervised Semantic Segmentation
论文作者
论文摘要
我们提出了一个因果推理框架，以改善弱监督的语义分割（WSSS）。具体而言，我们旨在通过仅使用图像级标签（WSSS中最关键的步骤）来生成更好的像素级伪面罩。我们将伪面罩的模棱两可界限的原因归因于混杂的上下文，例如，“马”和“人”的正确图像级分类不仅可能是由于对每个实例的识别，而且还因为它们的共发生上下文而导致了模型检查（例如（例如，CAM））很难区分边界。受此启发，我们提出了一个结构性因果模型，以分析图像，上下文和类标签之间的因果关系。基于它，我们开发了一种新方法：上下文调整（CONTA），以消除图像级分类中的混杂偏置，从而为后续分割模型提供更好的伪掩模作为基础真相。在Pascal VOC 2012和MS-Coco上，我们表明Conta将各种流行的WSS方法推向新的最新技术。
We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only image-level labels -- the most crucial step in WSSS. We attribute the cause of the ambiguous boundaries of pseudo-masks to the confounding context, e.g., the correct image-level classification of "horse" and "person" may be not only due to the recognition of each instance, but also their co-occurrence context, making the model inspection (e.g., CAM) hard to distinguish between the boundaries. Inspired by this, we propose a structural causal model to analyze the causalities among images, contexts, and class labels. Based on it, we develop a new method: Context Adjustment (CONTA), to remove the confounding bias in image-level classification and thus provide better pseudo-masks as ground-truth for the subsequent segmentation model. On PASCAL VOC 2012 and MS-COCO, we show that CONTA boosts various popular WSSS methods to new state-of-the-arts.
