Skip to content

Latest commit

 

History

History
295 lines (281 loc) · 12.1 KB

File metadata and controls

295 lines (281 loc) · 12.1 KB

Real-time semantic segmentation for autonomous driving: A review of CNNs, Transformers, and Beyond: [JKSUCI].

Summary of Contents

This repo is used for recording, tracking several real-time semantic segmentation for autonmous driving

  • Methods: A Survey -->

    Methods: A Survey

    FCN-like Network

    Method Year Venue Title Paper Code Dataset
    ENet 2016 Arxiv ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation Paper Code Cityscapes, CamVid
    ERFNet 2017 T-ITS ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation Paper Code Cityscapes, Camvid
    DABNet 2019 BMVC DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation Paper Code Cityscapes, CamVid
    LiteSeg 2019 DICTA LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation Paper Code Cityscapes, CamVid

    Transformer-based Networks

    Method Year Venue Paper Title Code Dataset
    SegFormer 2021 NeurIPS SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers Paper Code Cityscapes, ADE20K
    AFFormer 2023 AAAI Head-Free Lightweight Semantic Segmentation with Linear Transformer Paper Code Cityscapes, ADE20K
    SeaFormer 2023 ICLR SEAFORMER: SQUEEZE-ENHANCED AXIAL TRANSFORMER FOR MOBILE SEMANTIC SEGMENTATION Paper Code Cityscapes, ADE20K, PascalContext, COCO-Stuff

    Two-branch Network

    Method Year Venue Title Paper Code Dataset
    BiSeNet 2018 ECCV BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation Paper Code Cityscapes, CamVid, COCO-Stuff
    Fast-SCNN 2019 BMVC Fast-SCNN: Fast Semantic Segmentation Network Paper Code Cityscapes
    BiSeNetV2 2021 IJCV BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation Paper Code Cityscapes, CamVid, COCO-Stuff
    STDC 2021 CVPR Rethinking BiSeNet For Real-time Semantic Segmentation Paper Code Cityscapes, CamVid
    DSANet 2021 ESWA DSANet: Dilated spatial attention for real-time semantic segmentation in urban street scenes Paper Code Cityscapes, CamVid
    DDRNet 2022 T-ITS Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Traffic Scenes Paper Code Cityscapes, CamVid, COCO-Stuff

    Multi Branch Networks

    Method Year Venue Title Paper Code Dataset
    ICNet 2018 ECCV ICNet for Real-Time Semantic Segmentation on High-Resolution Images Paper Code Cityscapes, CamVid
    ESPNet 2018 ECCV ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation Paper Code Cityscapes, PascalVOC
    DFANet 2019 CVPR DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation Paper Code Cityscapes, CamVid
    PIDNet 2023 CVPR PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers Paper Code Cityscapes, CamVid,PASCAL Context

    Citation

    If you find this work useful in your research, please consider citing.

    @article{elhassan2024real,
      title={Real-time semantic segmentation for autonomous driving: A review of CNNs, Transformers, and Beyond},
      author={Elhassan, Mohammed AM and Zhou, Changjun and Khan, Ali and Benabid, Amina and Adam, Abuzar BM and Mehmood, Atif and Wambugu, Naftaly},
      journal={Journal of King Saud University-Computer and Information Sciences},
      pages={102226},
      year={2024},
      publisher={Elsevier}
    }