Object Boundary Guided Semantic Segmentation

TL;DR

This paper introduces OBG-FCN, a novel neural network that integrates object boundary information with semantic segmentation to improve pixel-level labeling accuracy, addressing limitations of previous FCN methods.

Contribution

The paper proposes a double-branch FCN that incorporates object boundary guidance into semantic segmentation, enhancing detail delineation and segmentation quality.

Findings

Significant improvement on PASCAL VOC benchmark

Effective integration of boundary and class features

End-to-end trainable segmentation system

Abstract

Semantic segmentation is critical to image content understanding and object localization. Recent development in fully-convolutional neural network (FCN) has enabled accurate pixel-level labeling. One issue in previous works is that the FCN based method does not exploit the object boundary information to delineate segmentation details since the object boundary label is ignored in the network training. To tackle this problem, we introduce a double branch fully convolutional neural network, which separates the learning of the desirable semantic class labeling with mask-level object proposals guided by relabeled boundaries. This network, called object boundary guided FCN (OBG-FCN), is able to integrate the distinct properties of object shape and class features elegantly in a fully convolutional way with a designed masking architecture. We conduct experiments on the PASCAL VOC segmentation benchmark, and show that the end-to-end trainable OBG-FCN system offers great improvement in optimizing the target semantic segmentation quality.