# PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model

arXiv: https://arxiv.org/abs/2204.02681 · HTML: https://mlsanity.com/paper/2204.02681/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 30 references that are in the map.
- First posted on arXiv 6 Apr 2022.

## Builds on (most cited first, 26 of 26)

- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://mlsanity.com/paper/2004.02147/) (2020)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)
- [ICNet for Real-Time Semantic Segmentation on High-Resolution Images](https://mlsanity.com/paper/1704.08545/) (2017)
- [Learning Lightweight Lane Detection CNNs by Self Attention Distillation](https://mlsanity.com/paper/1908.00821/) (2019)
- [ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation](https://mlsanity.com/paper/1803.06815/) (2018)
- [Semantic Flow for Fast and Accurate Scene Parsing](https://mlsanity.com/paper/2002.10120/) (2020)
- [Rethinking BiSeNet For Real-time Semantic Segmentation](https://mlsanity.com/paper/2104.13188/) (2021)
- [In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images](https://mlsanity.com/paper/1903.08469/) (2019)
- [DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1904.02216/) (2019)
- [ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network](https://mlsanity.com/paper/1811.11431/) (2018)
- [FaPN: Feature-aligned Pyramid Network for Dense Image Prediction](https://mlsanity.com/paper/2108.07058/) (2021)
- [FasterSeg: Searching for Faster Real-time Semantic Segmentation](https://mlsanity.com/paper/1912.10917/) (2019)
- [AlignSeg: Feature-Aligned Segmentation Networks](https://mlsanity.com/paper/2003.00872/) (2020)
- [EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow](https://mlsanity.com/paper/2109.09406/) (2021)
- [PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation](https://mlsanity.com/paper/2101.06175/) (2021)
- [Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones](https://mlsanity.com/paper/2103.05959/) (2021)
- [AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing](https://mlsanity.com/paper/2103.05930/) (2021)
- [PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset](https://mlsanity.com/paper/2112.07146/) (2021)

## Built on by (most cited first, 30 of 33)

- [PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers](https://mlsanity.com/paper/2206.02066/) (2022)
- [The GOOSE Dataset for Perception in Unstructured Environments](https://mlsanity.com/paper/2310.16788/) (2023)
- [Frequency-Adaptive Dilated Convolution for Semantic Segmentation](https://mlsanity.com/paper/2403.05369/) (2024)
- [Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness](https://mlsanity.com/paper/2503.18445/) (2025)
- [A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models](https://mlsanity.com/paper/2401.11311/) (2024)
- [WaterVG: Waterway Visual Grounding based on Text-Guided Vision and mmWave Radar](https://mlsanity.com/paper/2403.12686/) (2024)
- [Excavating in the Wild: The GOOSE-Ex Dataset for Semantic Segmentation](https://mlsanity.com/paper/2409.18788/) (2024)
- [CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspections](https://mlsanity.com/paper/2403.03063/) (2024)
- [SFNet: Faster and Accurate Semantic Segmentation via Semantic Flow](https://mlsanity.com/paper/2207.04415/) (2022)
- [EISeg: An Efficient Interactive Segmentation Tool based on PaddlePaddle](https://mlsanity.com/paper/2210.08788/) (2022)
- [Real-time High-Resolution Neural Network with Semantic Guidance for Crack Segmentation](https://mlsanity.com/paper/2307.00270/) (2023)
- [MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation](https://mlsanity.com/paper/2503.06700/) (2025)
- [EdgeNAT: Transformer for Efficient Edge Detection](https://mlsanity.com/paper/2408.10527/) (2024)
- [DSNet: A Novel Way to Use Atrous Convolutions in Semantic Segmentation](https://mlsanity.com/paper/2406.03702/) (2024)
- [Golden Cudgel Network for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2503.03325/) (2025)
- [Uncertainty in Real-Time Semantic Segmentation on Embedded Systems](https://mlsanity.com/paper/2301.01201/) (2022)
- [Cross-CBAM: A Lightweight network for Scene Segmentation](https://mlsanity.com/paper/2306.02306/) (2023)
- [OCTScenes: A Versatile Real-World Dataset of Tabletop Scenes for Object-Centric Learning](https://mlsanity.com/paper/2306.09682/) (2023)
- [The revenge of BiSeNet: Efficient Multi-Task Image Segmentation](https://mlsanity.com/paper/2404.09570/) (2024)
- [Reparameterizable Dual-Resolution Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/2406.12496/) (2024)
- [TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency](https://mlsanity.com/paper/2210.05152/) (2022)
- [NNPP: A Learning-Based Heuristic Model for Accelerating Optimal Path Planning on Uneven Terrain](https://mlsanity.com/paper/2308.04792/) (2023)
- [Bilateral Network with Residual U-blocks and Dual-Guided Attention for Real-time Semantic Segmentation](https://mlsanity.com/paper/2310.20305/) (2023)
- [CSFNet: A Cosine Similarity Fusion Network for Real-Time RGB-X Semantic Segmentation of Driving Scenes](https://mlsanity.com/paper/2407.01328/) (2024)
- [Distortion-Aware Network Pruning and Feature Reuse for Real-time Video Segmentation](https://mlsanity.com/paper/2206.09604/) (2022)
- [Spatial-Assistant Encoder-Decoder Network for Real Time Semantic Segmentation](https://mlsanity.com/paper/2309.10519/) (2023)
- [Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects](https://mlsanity.com/paper/2309.12641/) (2023)
- [P2AT: Pyramid Pooling Axial Transformer for Real-time Semantic Segmentation](https://mlsanity.com/paper/2310.15025/) (2023)
- [Autonomous Robotic Drilling System for Mice Cranial Window Creation](https://mlsanity.com/paper/2406.14135/) (2024)
- [ICFRNet: Image Complexity Prior Guided Feature Refinement for Real-time Semantic Segmentation](https://mlsanity.com/paper/2408.13771/) (2024)

## Abstract (arXiv)

Real-world applications have high demands for semantic segmentation methods. Although semantic segmentation has made remarkable leap-forwards with deep learning, the performance of real-time methods is not satisfactory. In this work, we propose PP-LiteSeg, a novel lightweight model for the real-time semantic segmentation task. Specifically, we present a Flexible and Lightweight Decoder (FLD) to reduce computation overhead of previous decoder. To strengthen feature representations, we propose a Unified Attention Fusion Module (UAFM), which takes advantage of spatial and channel attention to produce a weight and then fuses the input features with the weight. Moreover, a Simple Pyramid Pooling Module (SPPM) is proposed to aggregate global context with low computation cost. Extensive evaluations demonstrate that PP-LiteSeg achieves a superior trade-off between accuracy and speed compared to other methods. On the Cityscapes test set, PP-LiteSeg achieves 72.0% mIoU/273.6 FPS and 77.5% mIoU/102.6 FPS on NVIDIA GTX 1080Ti. Source code and models are available at PaddleSeg: https://github.com/PaddlePaddle/PaddleSeg.