ELANet: Effective Lightweight Attention-Guided Network for Real-Time Semantic Segmentation

ELANet: Effective Lightweight Attention-Guided Network for Real-Time Semantic Segmentation
复制标题

DOI：
10.1007/s11063-023-11145-z
复制
发表时间：
2023-01
期刊：
Neural Processing Letters
影响因子：
3.1
通讯作者：
Qingming Yi;Guoshuai Dai;Min Shi;Zunkai Huang;Aiwen Luo
Qingming Yi;Guoshuai Dai;Min Shi;Zunkai Huang;Aiwen Luo
中科院分区：
计算机科学4区
文献类型：
--
作者：
Qingming Yi;Guoshuai Dai;Min Shi;Zunkai Huang;Aiwen Luo

文献摘要

相似文献

深度神经网络极大地促进了语义分割的应用。然而，大多数现有的神经网络为了实现更高的精度而带来大量模型参数的大量计算，这对于资源有限的边缘设备来说是无法承受的。为了在计算效率和分割精度之间实现适当的权衡，我们在这项工作中提出了一种基于非对称编码器-解码器框架的有效的轻量级注意力引导网络（ELANet），用于实时语义分割。在编码阶段，我们结合了空洞卷积和深度卷积来设计两种有效的上下文引导块来学习上下文语义信息。解码器中开发了具有双注意力引导融合（DAF）单元的精细特征融合模块，以利用不同级别的特征。在没有任何预训练的情况下，我们通过在输入分辨率为 5121024 的 Cityscapes 数据集上进行大量实验来估计多注意力 ELANet 的性能，在单个 3090 GPU 上仅使用 0.76 M 参数和 10.34 GFLOPs 即可获得 75.4% mIoU 和 83 FPS 推理速度。该代码可在 https://github.com/DGS666/ELANet 上公开获取。
Deep neural networks have greatly facilitated the applications of semantic segmentation. However, most of the existing neural networks bring massive calculations with lots of model parameters for achieving a higher precision, which is unaffordable for resource-constrained edge devices. To achieve an appropriate trade-off between computing efficiency and segmentation accuracy, we proposed an effective lightweight attention-guided network (ELANet) for real-time semantic segmentation based on an asymmetrical encoder–decoder framework in this work. In the encoding phase, we combined atrous convolution and depth-wise convolution to design two types of effective context guidance blocks to learn contextual semantic information. A refined feature fusion module with a dual attention-guided fusion (DAF) unit was developed in the decoder to exploit different levels of features. Without any pretraining, we estimated the performance of multi-attention ELANet with extensive experiments on the Cityscapes dataset with an input resolution of 5121024, resulting in 75.4% mIoU and 83 FPS inference speed with only 0.76 M parameters and 10.34 GFLOPs on a single 3090 GPU. The code is publicly available at https://github.com/DGS666/ELANet.