DeepAI AI Chat
Log In Sign Up

Boundary Guided Context Aggregation for Semantic Segmentation

by   Haoxiang Ma, et al.

The recent studies on semantic segmentation are starting to notice the significance of the boundary information, where most approaches see boundaries as the supplement of semantic details. However, simply combing boundaries and the mainstream features cannot ensure a holistic improvement of semantics modeling. In contrast to the previous studies, we exploit boundary as a significant guidance for context aggregation to promote the overall semantic understanding of an image. To this end, we propose a Boundary guided Context Aggregation Network (BCANet), where a Multi-Scale Boundary extractor (MSB) borrowing the backbone features at multiple scales is specifically designed for accurate boundary detection. Based on which, a Boundary guided Context Aggregation module (BCA) improved from Non-local network is further proposed to capture long-range dependencies between the pixels in the boundary regions and the ones inside the objects. By aggregating the context information along the boundaries, the inner pixels of the same category achieve mutual gains and therefore the intra-class consistency is enhanced. We conduct extensive experiments on the Cityscapes and ADE20K databases, and comparable results are achieved with the state-of-the-art methods, clearly demonstrating the effectiveness of the proposed one.


page 1

page 2

page 4

page 8

page 9


Attention-guided Chained Context Aggregation for Semantic Segmentation

Recent breakthroughs in semantic segmentation methods based on Fully Con...

Boundary-aware Graph Reasoning for Semantic Segmentation

In this paper, we propose a Boundary-aware Graph Reasoning (BGR) module ...

DCAN: Improving Temporal Action Detection via Dual Context Aggregation

Temporal action detection aims to locate the boundaries of action in the...

Context Prior for Scene Segmentation

Recent works have widely explored the contextual dependencies to achieve...

Boundary Knowledge Translation based Reference Semantic Segmentation

Given a reference object of an unknown type in an image, human observers...

ElegantSeg: End-to-End Holistic Learning for Extra-Large Image Semantic Segmentation

This paper presents a new paradigm for Extra-large image semantic Segmen...

A Unified Efficient Pyramid Transformer for Semantic Segmentation

Semantic segmentation is a challenging problem due to difficulties in mo...