# Semantic Flow for Fast and Accurate Scene Parsing

arXiv: https://arxiv.org/abs/2002.10120 · HTML: https://mlsanity.com/paper/2002.10120/

## Key facts

- Cited by 128 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Feb 2020.

## Built on by (most cited first, 30 of 128)

- [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://mlsanity.com/paper/2209.08575/) (2022)
- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation](https://mlsanity.com/paper/2203.15224/) (2022)
- [OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding](https://mlsanity.com/paper/2406.19389/) (2024)
- [Rethinking BiSeNet For Real-time Semantic Segmentation](https://mlsanity.com/paper/2104.13188/) (2021)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes](https://mlsanity.com/paper/2101.06085/) (2021)
- [PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers](https://mlsanity.com/paper/2206.02066/) (2022)
- [TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation](https://mlsanity.com/paper/2204.05525/) (2022)
- [FaPN: Feature-aligned Pyramid Network for Dense Image Prediction](https://mlsanity.com/paper/2108.07058/) (2021)
- [Changer: Feature Interaction is What You Need for Change Detection](https://mlsanity.com/paper/2209.08290/) (2022)
- [Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively](https://mlsanity.com/paper/2401.02955/) (2024)
- [OMG-Seg: Is One Model Good Enough For All Segmentation?](https://mlsanity.com/paper/2401.10229/) (2024)
- [SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More](https://mlsanity.com/paper/2408.04579/) (2024)
- [SeMask: Semantically Masked Transformers for Semantic Segmentation](https://mlsanity.com/paper/2112.12782/) (2021)
- [SAM Fails to Segment Anything? -- SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, Medical Image Segmentation, and More](https://mlsanity.com/paper/2304.09148/) (2023)
- [Learning Statistical Texture for Semantic Segmentation](https://mlsanity.com/paper/2103.04133/) (2021)
- [Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism](https://mlsanity.com/paper/2309.11331/) (2023)
- [Towards Robust Referring Image Segmentation](https://mlsanity.com/paper/2209.09554/) (2022)
- [Enhanced Boundary Learning for Glass-like Object Segmentation](https://mlsanity.com/paper/2103.15734/) (2021)
- [Towards Semantic Equivalence of Tokenization in Multimodal LLM](https://mlsanity.com/paper/2406.05127/) (2024)
- [Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review](https://mlsanity.com/paper/2305.05813/) (2023)
- [EdgeSAM: Prompt-In-the-Loop Distillation for SAM](https://mlsanity.com/paper/2312.06660/) (2023)
- [EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow](https://mlsanity.com/paper/2109.09406/) (2021)
- [SuperFusion: Multilevel LiDAR-Camera Fusion for Long-Range HD Map Generation](https://mlsanity.com/paper/2211.15656/) (2022)
- [Continual Semantic Segmentation with Automatic Memory Sample Selection](https://mlsanity.com/paper/2304.05015/) (2023)
- [Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation](https://mlsanity.com/paper/2204.04655/) (2022)
- [Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation](https://mlsanity.com/paper/2207.08485/) (2022)
- [Rethinking Mobile Block for Efficient Attention-based Models](https://mlsanity.com/paper/2301.01146/) (2023)
- [Multi-Task Learning with Multi-Query Transformer for Dense Prediction](https://mlsanity.com/paper/2205.14354/) (2022)

## Abstract (arXiv)

In this paper, we focus on designing effective method for fast and accurate scene parsing. A common practice to improve the performance is to attain high resolution feature maps with strong semantic representation. Two strategies are widely used -- atrous convolutions and feature pyramid fusion, are either computation intensive or ineffective. Inspired by the Optical Flow for motion alignment between adjacent video frames, we propose a Flow Alignment Module (FAM) to learn Semantic Flow between feature maps of adjacent levels, and broadcast high-level features to high resolution features effectively and efficiently. Furthermore, integrating our module to a common feature pyramid structure exhibits superior performance over other real-time methods even on light-weight backbone networks, such as ResNet-18. Extensive experiments are conducted on several challenging datasets, including Cityscapes, PASCAL Context, ADE20K and CamVid. Especially, our network is the first to achieve 80.4% mIoU on Cityscapes with a frame rate of 26 FPS. The code is available at urlhttps://github.com/lxtGH/SFSegNets.