像素级域适应：增强弱监督语义分割的新视角
Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation
AI总结：
针对图像级WSSS中CAM仅激活判别性部位导致伪掩码不完整的问题，提出像素级域适应PLDA，通过多头对抗域分类器与置信伪监督学习像素域不变特征。
摘要：
近来，大量注意力被投入到仅从图像标签学习语义分割模型这一追求中，该范式被称为图像级弱监督语义分割（WSSS）。现有尝试采用类激活图（CAMs）作为先验来挖掘目标区域，却观察到激活不平衡的问题，即只有最具判别力的目标部位被定位。本文认为，目标的判别性部位与非判别性部位之间的分布差异，阻碍了模型生成完整且精确的伪掩码作为真值。为此，我们提出一种像素级域适应（PLDA）方法，以促使模型学习像素级域不变特征。具体而言，引入一个与特征提取进行对抗训练的多头域分类器，以促进像素特征的形成，这些特征对于源域（即判别性目标部位）与目标域（即非判别性目标部位）之间的偏移具有不变性。此外，我们提出一种置信伪监督策略，以保证每个像素在分割任务中的判别能力，作为图像内域对抗训练的补充。我们的方法在概念上简单、直观，并且能够轻松集成到现有WSSS方法中。以若干强基线模型为例，我们通过实验证明了本方法在广泛设置下的有效性。
英文摘要：
Recent attention has been devoted to the pursuit of learning semantic segmentation models exclusively from image tags, a paradigm known as image-level Weakly Supervised Semantic Segmentation (WSSS). Existing attempts adopt the Class Activation Maps (CAMs) as priors to mine object regions yet observe the imbalanced activation issue, where only the most discriminative object parts are located. In this paper, we argue that the distribution discrepancy between the discriminative and the non-discriminative parts of objects prevents the model from producing complete and precise pseudo masks as ground truths. For this purpose, we propose a Pixel-Level Domain Adaptation (PLDA) method to encourage the model in learning pixel-wise domain-invariant features. Specifically, a multi-head domain classifier trained adversarially with the feature extraction is introduced to promote the emergence of pixel features that are invariant with respect to the shift between the source (i.e., the discriminative object parts) and the target (\textit{i.e.}, the non-discriminative object parts) domains. In addition, we come up with a Confident Pseudo-Supervision strategy to guarantee the discriminative ability of each pixel for the segmentation task, which serves as a complement to the intra-image domain adversarial training. Our method is conceptually simple, intuitive and can be easily integrated into existing WSSS methods. Taking several strong baseline models as instances, we experimentally demonstrate the effectiveness of our approach under a wide range of settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
