Boundary-Aware Feature Propagation for Scene Segmentation
Preprint
Abstract
In this work, we address the challenging issue of scene segmentation. To increase the feature similarity of the same object while keeping the feature discrimination of different objects, we explore to propagate information throughout the image under the control of objects' boundaries. To this end, we first propose to learn the boundary as an additional semantic class to enable the network to be aware of the boundary layout. Then, we propose unidirectional acyclic graphs (UAGs) to model the function of undirected cyclic graphs (UCGs), which structurize the image via building graphic pixel-by-pixel connections, in an efficient and effective way. Furthermore, we propose a boundary-aware feature propagation (BFP) module to harvest and propagate the local features within their regions isolated by the learned boundaries in the UAG-structured image. The proposed BFP is capable of splitting the feature propagation into a set of semantic groups via building strong connections among the same segment region but weak connections between different segment regions. Without bells and whistles, our approach achieves new state-of-the-art segmentation performance on three challenging semantic segmentation datasets, i.e., PASCAL-Context, CamVid, and Cityscapes.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Unpaired Image Captioning via Scene Graph Alignments2019
- Scene Graph Generation With External Knowledge and Image Reconstruction2019
- Wider or Deeper: Revisiting the ResNet Model for Visual RecognitionPattern Recognition, 2019
- Toward Achieving Robust Low-Level and High-Level Scene ParsingIEEE Transactions on Image Processing, 2018
- Unpaired Image Captioning by Language Pivoting2018
- PSANet: Point-wise Spatial Attention Network for Scene Parsing2018
- Learning a Discriminative Feature Network for Semantic Segmentation2018
- Kernelized Subspace Ranking for Saliency Detection2016
- Robust Higher Order Potentials for Enforcing Label ConsistencyInternational Journal of Computer Vision, 2009
- Statistical edge detection: learning and evaluating edge cuesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003