Multi-Attention-Network for Semantic Segmentation of High-Resolution Remote Sensing Images

Explore this paper's citation graph

Summary

A novel attention mechanism named kernel attention with linear complexity is proposed to alleviate the high computational demand of attention and integrate local feature maps extracted by ResNeXt-101 with their corresponding global dependencies, and adaptively signalize interdependent channel maps.

Type
article
Published
2020-09-03
Cited by
31
References
60

Keywords

Computer science, Segmentation, Encoder, Feature (linguistics), Artificial intelligence

References

Cited by

Related papers