DeepAI AI Chat
Log In Sign Up

BiCANet: Bi-directional Contextual Aggregating Network for Image Semantic Segmentation

by   Quan Zhou, et al.
Temple University
Nanjing University of Posts and Telecommunications
Tencent QQ

Exploring contextual information in convolution neural networks (CNNs) has gained substantial attention in recent years for semantic segmentation. This paper introduces a Bi-directional Contextual Aggregating Network, called BiCANet, for semantic segmentation. Unlike previous approaches that encode context in feature space, BiCANet aggregates contextual cues from a categorical perspective, which is mainly consist of three parts: contextual condensed projection block (CCPB), bi-directional context interaction block (BCIB), and muti-scale contextual fusion block (MCFB). More specifically, CCPB learns a category-based mapping through a split-transform-merge architecture, which condenses contextual cues with different receptive fields from intermediate layer. BCIB, on the other hand, employs dense skipped-connections to enhance the class-level context exchanging. Finally, MCFB integrates multi-scale contextual cues by investigating short- and long-ranged spatial dependencies. To evaluate BiCANet, we have conducted extensive experiments on three semantic segmentation datasets: PASCAL VOC 2012, Cityscapes, and ADE20K. The experimental results demonstrate that BiCANet outperforms recent state-of-the-art networks without any postprocess techniques. Particularly, BiCANet achieves the mIoU score of 86.7 Cityscapes and ADE20K testset, respectively.


page 1

page 4

page 8

page 9


CTNet: Context-based Tandem Network for Semantic Segmentation

Contextual information has been shown to be powerful for semantic segmen...

Complementary Bi-directional Feature Compression for Indoor 360° Semantic Segmentation with Self-distillation

Recently, horizontal representation-based panoramic semantic segmentatio...

Is the U-Net Directional-Relationship Aware?

CNNs are often assumed to be capable of using contextual information abo...

Learning to Predict Context-adaptive Convolution for Semantic Segmentation

Long-range contextual information is essential for achieving high-perfor...

Probability Map Guided Bi-directional Recurrent UNet for Pancreas Segmentation

Pancreatic cancer is one of the most lethal cancers as incidence approxi...

Improving Fully Convolution Network for Semantic Segmentation

Fully Convolution Networks (FCN) have achieved great success in dense pr...

Attention-guided Chained Context Aggregation for Semantic Segmentation

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