DeepAI AI Chat
Log In Sign Up

Attention-based fusion of semantic boundary and non-boundary information to improve semantic segmentation

by   Jefferson Fontinele, et al.
UFBA em Pauta

This paper introduces a method for image semantic segmentation grounded on a novel fusion scheme, which takes place inside a deep convolutional neural network. The main goal of our proposal is to explore object boundary information to improve the overall segmentation performance. Unlike previous works that combine boundary and segmentation features, or those that use boundary information to regularize semantic segmentation, we instead propose a novel approach that embodies boundary information onto segmentation. For that, our semantic segmentation method uses two streams, which are combined through an attention gate, forming an end-to-end Y-model. To the best of our knowledge, ours is the first work to show that boundary detection can improve semantic segmentation when fused through a semantic fusion gate (attention model). We performed an extensive evaluation of our method over public data sets. We found competitive results on all data sets after comparing our proposed model with other twelve state-of-the-art segmenters, considering the same training conditions. Our proposed model achieved the best mIoU on the CityScapes, CamVid, and Pascal Context data sets, and the second best on Mapillary Vistas.


page 2

page 11


Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts

In this paper, we present a joint multi-task learning framework for sema...

SHDM-NET: Heat Map Detail Guidance with Image Matting for Industrial Weld Semantic Segmentation Network

In actual industrial production, the assessment of the steel plate weldi...

Boundary-sensitive Network for Portrait Segmentation

Compared to the general semantic segmentation problem, portrait segmenta...

A Unified Efficient Pyramid Transformer for Semantic Segmentation

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

Robust Fusion for Bayesian Semantic Mapping

The integration of semantic information in a map allows robots to unders...

Semantic Diffusion Network for Semantic Segmentation

Precise and accurate predictions over boundary areas are essential for s...