Semantic Segmentation with Boundary Neural Fields

Abstract

The state-of-the-art in semantic segmentation is currently represented by fully convolutional networks (FCNs). However, FCNs use large receptive fields and many pooling layers, both of which cause blurring and low spatial resolution in the deep layers. As a result FCNs tend to produce segmentations that are poorly localized around object boundaries. Prior work has attempted to address this issue in post-processing steps, for example using a color-based CRF on top of the FCN predictions. However, these approaches require additional parameters and low-level features that are difficult to tune and integrate into the original network architecture. Additionally, most CRFs use color-based pixel affinities, which are not well suited for semantic segmentation and lead to spatially disjoint predictions. To overcome these problems, we introduce a Boundary Neural Field (BNF), which is a global energy model integrating FCN predictions with boundary cues. The boundary information is used to enhance semantic segment coherence and to improve object localization. Specifically, we first show that the convolutional filters of semantic FCNs provide good features for boundary detection. We then employ the predicted boundaries to define pairwise potentials in our energy. Finally, we show that our energy decomposes semantic segmentation into multiple binary problems, which can be relaxed for efficient global optimization. We report extensive experiments demonstrating that minimization of our global boundary-based energy yields results superior to prior globalization methods, both quantitatively as well as qualitatively.

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Simultaneous Detection and Segmentation
• BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
• Feedforward semantic segmentation with zoom-out features
• DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection

Cited by in corpus (3)

• ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
• InstanceCut: from Edges to Instances with MultiCut
• Object Boundary Guided Semantic Segmentation