Papers › GSANet: Semantic Segmentation with Global and Selective Attention

GSANet: Semantic Segmentation with Global and Selective Attention

14 Feb 2020arXiv:2003.00830archive 2025-07-28

Qing-Feng Liu, Mostafa El-Khamy, Dongwoon Bai, Jungwon Lee

This paper proposes a novel deep learning architecture for semantic segmentation. The proposed Global and Selective Attention Network (GSANet) features Atrous Spatial Pyramid Pooling (ASPP) with a novel sparsemax global attention and a novel selective attention that deploys a condensation and diffusion mechanism to aggregate the multi-scale contextual information from the extracted deep features. A selective attention decoder is also proposed to process the GSA-ASPP outputs for optimizing the softmax volume. We are the first to benchmark the performance of semantic segmentation networks with the low-complexity feature extraction network (FXN) MobileNetEdge, that is optimized for low latency on edge devices. We show that GSANet can result in more accurate segmentation with MobileNetEdge, as well as with strong FXNs, such as Xception. GSANet improves the state-of-art semantic segmentation accuracy on both the ADE20k and the Cityscapes datasets.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Decoder Segmentation Semantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: IGSA

1x1 Convolution Average Pooling Convolution Dense Connections Depthwise Convolution Depthwise Separable Convolution Global Average Pooling IGSA Max Pooling Pointwise Convolution ReLU Residual Connection Softmax Sparsemax Spatial Pyramid Pooling

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections