# Feature Pyramid Encoding Network for Real-time Semantic Segmentation

arXiv: https://arxiv.org/abs/1909.08599 · HTML: https://mlsanity.com/paper/1909.08599/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2019.

## Built on by (most cited first, 13 of 13)

- [LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2107.08623/) (2021)
- [Enhanced Boundary Learning for Glass-like Object Segmentation](https://mlsanity.com/paper/2103.15734/) (2021)
- [Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World](https://mlsanity.com/paper/2107.03172/) (2021)
- [Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance](https://mlsanity.com/paper/2108.09174/) (2021)
- [Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA Experts](https://mlsanity.com/paper/2412.04220/) (2024)
- [Segmenting Transparent Object in the Wild with Transformer](https://mlsanity.com/paper/2101.08461/) (2021)
- [Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN](https://mlsanity.com/paper/2302.10484/) (2023)
- [HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation](https://mlsanity.com/paper/2407.07441/) (2024)
- [Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing](https://mlsanity.com/paper/2309.06047/) (2023)
- [JetSeg: Efficient Real-Time Semantic Segmentation Model for Low-Power GPU-Embedded Systems](https://mlsanity.com/paper/2305.11419/) (2023)
- [Latent Graph Attention for Enhanced Spatial Context](https://mlsanity.com/paper/2307.04149/) (2023)
- [Efficient Semantic Segmentation via Lightweight Multiple-Information Interaction Network](https://mlsanity.com/paper/2410.02224/) (2024)
- [ECMNet:Lightweight Semantic Segmentation with Efficient CNN-Mamba Network](https://mlsanity.com/paper/2506.08629/) (2025)

## Abstract (arXiv)

Although current deep learning methods have achieved impressive results for semantic segmentation, they incur high computational costs and have a huge number of parameters. For real-time applications, inference speed and memory usage are two important factors. To address the challenge, we propose a lightweight feature pyramid encoding network (FPENet) to make a good trade-off between accuracy and speed. Specifically, we use a feature pyramid encoding block to encode multi-scale contextual features with depthwise dilated convolutions in all stages of the encoder. A mutual embedding upsample module is introduced in the decoder to aggregate the high-level semantic features and low-level spatial details efficiently. The proposed network outperforms existing real-time methods with fewer parameters and improved inference speed on the Cityscapes and CamVid benchmark datasets. Specifically, FPENet achieves 68.0% mean IoU on the Cityscapes test set with only 0.4M parameters and 102 FPS speed on an NVIDIA TITAN V GPU.