论文标题
em-paste：EM引导的切割和dall-e增强型，用于图像级弱监督的实例分段
EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation
论文作者
论文摘要
我们提出EM-Paste：一种期望最大化（EM）指导的切割型组成数据集增强方法，用于仅使用图像级监督进行弱监督的实例分割。提出的方法由三个主要组成部分组成。第一个组件会生成高质量的前景对象蒙版。为此，提出了一种类似于EM的方法，它可以迭代地完善一组通用区域建议方法生成的初始对象掩模建议。接下来，在第二个组件中，使用诸如dall-e（dall-e）的文本对图组成合成方法生成高质量的上下文感知背景图像。最后，第三个组件通过将前景对象掩盖合并到原始和生成的背景图像上，从而创建一个大型伪标记的实例分割训练数据集。所提出的方法通过仅使用图像级，弱标签信息来实现Pascal VOC 2012和MS Coco数据集的最先进的实例分割结果。特别是，它在Pascal和Coco上分别优于最佳基线+7.4和+2.8 Map0.50。此外，该方法通过选择性增强代表性不足的类，为长尾弱监督实例分割问题（当许多类可能只有培训样本很少）提供了新的解决方案。
We propose EM-PASTE: an Expectation Maximization(EM) guided Cut-Paste compositional dataset augmentation approach for weakly-supervised instance segmentation using only image-level supervision. The proposed method consists of three main components. The first component generates high-quality foreground object masks. To this end, an EM-like approach is proposed that iteratively refines an initial set of object mask proposals generated by a generic region proposal method. Next, in the second component, high-quality context-aware background images are generated using a text-to-image compositional synthesis method like DALL-E. Finally, the third component creates a large-scale pseudo-labeled instance segmentation training dataset by compositing the foreground object masks onto the original and generated background images. The proposed approach achieves state-of-the-art weakly-supervised instance segmentation results on both the PASCAL VOC 2012 and MS COCO datasets by using only image-level, weak label information. In particular, it outperforms the best baseline by +7.4 and +2.8 mAP0.50 on PASCAL and COCO, respectively. Further, the method provides a new solution to the long-tail weakly-supervised instance segmentation problem (when many classes may only have few training samples), by selectively augmenting under-represented classes.
