This paper studies co-segmenting the common semantic object in a set of
images. Existing works either rely on carefully engineered networks to mine the
implicit semantic information in visual features or require extra data (i.e.,
classification labels) for training. In this paper, we leverage the contrastive
language-image pre-training framework (CLIP) for the task. With a backbone
segmentation network that independently processes each image from the set, we
introduce semantics from CLIP into the backbone features, refining them in a
coarse-to-fine manner with three key modules: i) an image set feature
correspondence module, encoding global consistent semantic information of the
image set; ii) a CLIP interaction module, using CLIP-mined common semantics of
the image set to refine the backbone feature; iii) a CLIP regularization
module, drawing CLIP towards this co-segmentation task, identifying the best
CLIP semantic and using it to regularize the backbone feature. Experiments on
four standard co-segmentation benchmark datasets show that the performance of
our method outperforms state-of-the-art methods.

本文研究了在一组图像中共同语义对象的共同分割，并使用对比式语言 - 图像预训练框架 (CLIP) 来完成该任务。通过一个用于独立处理图像集中每个图像的骨干分割网络，我们引入了 CLIP 中的语义信息，并通过三个关键模块 ——i) 图像集特征对应模块，对图像集的全局一致语义信息进行编码；ii) CLIP 交互模块，利用 CLIP 提取的图像集的共同语义信息来优化骨干特征；iii) CLIP 正则化模块，引导 CLIP 朝向共同分割任务，找到最佳的 CLIP 语义并用其来正则化骨干特征 —— 以一种粗糙到精细的方式优化这些特征。在四个标准的共同分割基准数据集上的实验证明了我们方法的性能优于最先进的方法。