# LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation

arXiv: https://arxiv.org/abs/2006.02706 · HTML: https://mlsanity.com/paper/2006.02706/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2020.

## Built on by (most cited first, 5 of 5)

- [Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes](https://mlsanity.com/paper/2203.04031/) (2022)
- [Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN](https://mlsanity.com/paper/2302.10484/) (2023)
- [GA-NET: Global Attention Network for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2107.03101/) (2021)
- [LightLayers: Parameter Efficient Dense and Convolutional Layers for Image Classification](https://mlsanity.com/paper/2101.02268/) (2021)
- [STDC-MA Network for Semantic Segmentation](https://mlsanity.com/paper/2205.04639/) (2022)

## Abstract (arXiv)

The recent development of light-weighted neural networks has promoted the applications of deep learning under resource constraints and mobile applications. Many of these applications need to perform a real-time and efficient prediction for semantic segmentation with a light-weighted network. This paper introduces a light-weighted network with an efficient reduced non-local module (LRNNet) for efficient and realtime semantic segmentation. We proposed a factorized convolutional block in ResNet-Style encoder to achieve more lightweighted, efficient and powerful feature extraction. Meanwhile, our proposed reduced non-local module utilizes spatial regional dominant singular vectors to achieve reduced and more representative non-local feature integration with much lower computation and memory cost. Experiments demonstrate our superior trade-off among light-weight, speed, computation and accuracy. Without additional processing and pretraining, LRNNet achieves 72.2% mIoU on Cityscapes test dataset only using the fine annotation data for training with only 0.68M parameters and with 71 FPS on a GTX 1080Ti card.