Glass-like objects are widespread in daily life but remain intractable to be segmented for most existing methods. The transparent property makes it difficult to be distinguished from background, while the tiny separation boundary further impedes the acquisition of their exact contour. In this paper, by revealing the key co-evolution demand of semantic and boundary learning, we propose a Selective Mutual Evolution (SME) module to enable the reciprocal feature learning between them. Then to exploit the global shape context, we propose a Structurally Attentive Refinement (SAR) module to conduct a fine-grained feature refinement for those ambiguous points around the boundary. Finally, to further utilize the multi-scale representation, we integrate the above two modules into a cascaded structure and then introduce a Reciprocal Feature Evolution Network (RFENet) for effective glass-like object segmentation. Extensive experiments demonstrate that our RFENet achieves state-of-the-art performance on three popular public datasets.

翻译：玻璃类物体在日常生活中广泛存在，但多数现有方法仍难以对其实现准确分割。其透明特性使其难以与背景区分，而细微的分离边界进一步阻碍了精确轮廓的获取。本文通过揭示语义学习与边界学习的关键协同演化需求，提出选择性互惠演化模块以实现两者间的互惠特征学习；进而为利用全局形状上下文，提出结构注意力精炼模块，对边界周围模糊点进行细粒度特征精炼。最终为充分利用多尺度表征，将上述两个模块集成至级联结构中，构建了面向高效玻璃类物体分割的互惠特征演化网络。大量实验表明，所提RFENet在三个主流公开数据集上均取得了最优性能。