Weakly-supervised image segmentation (WSIS) is a critical task in computer
vision that relies on image-level class labels. Multi-stage training procedures
have been widely used in existing WSIS approaches to obtain high-quality
pseudo-masks as ground-truth, resulting in significant progress. However,
single-stage WSIS methods have recently gained attention due to their potential
for simplifying training procedures, despite often suffering from low-quality
pseudo-masks that limit their practical applications. To address this issue, we
propose a novel single-stage WSIS method that utilizes a siamese network with
contrastive learning to improve the quality of class activation maps (CAMs) and
achieve a self-refinement process. Our approach employs a cross-representation
refinement method that expands reliable object regions by utilizing different
feature representations from the backbone. Additionally, we introduce a
cross-transform regularization module that learns robust class prototypes for
contrastive learning and captures global context information to feed back rough
CAMs, thereby improving the quality of CAMs. Our final high-quality CAMs are
used as pseudo-masks to supervise the segmentation result. Experimental results
on the PASCAL VOC 2012 dataset demonstrate that our method significantly
outperforms other state-of-the-art methods, achieving 67.2% and 68.76% mIoU on
PASCAL VOC 2012 val set and test set, respectively. Furthermore, our method has
been extended to weakly supervised object localization task, and experimental
results demonstrate that our method continues to achieve very competitive
results.

弱监督图像分割是计算机视觉中的关键任务，依赖于图像级别的类别标签。我们提出了一种利用具有对比学习的孪生网络改进类别活动图 (CAMs) 质量并实现自我改善过程的新型单阶段 WSIS 方法。我们的方法在 PASCAL VOC 2012 数据集上实验证明其明显优于其他最先进方法，在 PASCAL VOC 2012 验证集和测试集上分别达到了 67.2% 和 68.76% mIoU。此外，我们的方法在弱监督目标定位任务中也展现出竞争力。