RFENet: Towards Reciprocal Feature Evolution for Glass Segmentation

TL;DR

RFENet introduces reciprocal feature evolution modules that enhance segmentation of transparent glass-like objects by co-evolving semantic and boundary features, achieving state-of-the-art results.

Contribution

The paper proposes a novel RFENet with SME and SAR modules for improved glass object segmentation, addressing transparency and boundary challenges.

Findings

Achieves state-of-the-art performance on three public datasets.

Effectively models co-evolution of semantic and boundary features.

Enhances boundary detail refinement around ambiguous regions.

Abstract

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.