- Learning Transferable Architectures for Scalable Image Recognition NASNet
- MnasNet: Platform-Aware Neural Architecture Search for Mobile MnasNet
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications MobileNets
- MobileNetV2: Inverted Residuals and Linear Bottlenecks MobileNetV2 MobileNetV2-pytorch
- MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks CVPR2018 code
- Searching for MobileNetV3 MobileNetV3 unofficial implementation MobileNetV3-for-Segmentation official TF Repo
- Efficient Net: Rethinking Model Scaling for Convolutional Neural Networks. ICML 2019 tfcode unofficial pytorch version
- MixNet: Mixed Depthwise Convolutional Kernels BMVC2019 Official TF Repo Unofficial pytporch
- EfficientNetV2: Smaller Models and Faster Training arxiv2021 EfficientNetV2
- Interleaved Group Convolutions for Deep Neural Networks IGCV
- IGCV2: Interleaved Structured Sparse Convolutional Neural Networks IGCV2
- IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks IGCV3
- Accelerating Deep Neural Networks with Spatial Bottleneck Modules arxiv2018
- Dynamic Convolution: Attention over Convolution Kernels arxiv2019
- Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution arxiv2019 unofficial implementation OctaveConv_pytorch OctaveConv_MXNet
- FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search arxiv2018 code
- ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation arxiv2018 code
- Hybrid Composition with IdleBlock: More Efficient Networks for Image Recognition arxiv2019
- FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions CVPR2020 FBNetv2
- FBNetV3: Joint Architecture-Recipe Search using Neural Acquisition Function arxiv2020
- FP-NAS: Fast Probabilistic Neural Architecture Search arxiv2020
- Fast and Accurate Model Scaling arxiv2021
- Mobile Computer Vision @ Facebook mobile-vision
- CVNets: High Performance Library for Computer Vision Technical report 4 Jun 2022 ml-cvnets
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices ShuffleNet
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design ShuffleNet V2 Shufflenet-v2-Pytorch
- ShuffleNetV2+:paper unrelease code ShuffleNet Series by Megvii Research
- WeightNet: Revisiting the Design Space of Weight Networks ECCV2020 WeightNet
- RepVGG: Making VGG-style ConvNets Great Again arxiv2020 RepVGG Tsinghua University, MEGVII Technology, etc
- CondenseNet: An Efficient DenseNet using Learned Group Convolutions CondenseNet
- CondenseNet V2: Sparse Feature Reactivation for Deep Networks CondenseNetV2
- ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification arxiv2019
- Seesaw-Net: Convolution Neural Network With Uneven Group Convolution arxiv2019
- ISBNet: Instance-aware Selective Branching Network arxiv2019
- Multinomial Distribution Learning for Effective Neural Architecture Search arxiv2019 code
- HGC: Hierarchical Group Convolution for Highcdly Efficient Neural Network arxiv2019
- DiCENet: Dimension-wise Convolutions for Efficient Networks arxiv2019 code
- Densely Connected Search Space for More Flexible Neural Architecture Search arxiv2019 code
- VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computing arxiv2019 Horizon Robotics
- VarGFaceNet: An Efficient Variable Group Convolutional Neural Network for Lightweight Face Recognition VarGFaceNet code Horizon Robotics (1st place in The Lightweight Face Recognition Challenge & Workshop ICCV 2019)
- Once for All: Train One Network and Specialize it for Efficient Deployment ICLR 2020 ofaNet MIT && MIT-IBM Watson AI Lab
- LPRNet: Lightweight Deep Network by Low-rank Pointwise Residual Convolution arxiv2019
- LeanConvNets: Low-cost Yet Effective Convolutional Neural Networks arxiv2019 Ben-Gurion University&&Emory Universit
- DeepSquare: Boosting the Learning Power of Deep Convolutional Neural Networks with Elementwise Square Operators arxiv2019 ByteDance AI Lab
- ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks arxiv2019 code Tianjin University
- XSepConv: Extremely Separated Convolution arxiv2020 Tsinghua University &&University College London
- GhostNet: More Features from Cheap Operations CVPR2020 TF Repo Huawei Noah’s Ark Lab&&Peking University&&Sydney University
- Resolution Adaptive Networks for Efficient Inference CVPR2020 RANet Tsinghua && HIT &&SenseTime
- TResNet: High Performance GPU-Dedicated Architecture arxiv2020 TResNet DAMO Academy, Alibaba Group
- Neural Architecture Design for GPU-Efficient Networks arxiv2020 Alibaba Group
- ReXNet: Diminishing Representational Bottleneck on Convolutional Neural Network arxiv2020 rexnet Clova AI Research, NAVER Corp
- Rethinking Bottleneck Structure for Efficient Mobile Network Design ECCV2020 MobileNeXt yitu-opensource
- Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets NeurIPS 2020**
- MicroNet: Towards Image Recognition with Extremely Low FLOPs arxiv2020 UC San Diego && Microsoft
- Lite-HRNet: A Lightweight High-Resolution Network cvpr2021 Lite-HRNet
- AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks MAI@CVPR 2021 AsymmNet
- ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation ENet
- ICNet for Real-Time Semantic Segmentation on High-Resolution Images ICNet
- Speeding up Semantic Segmentation for Autonomous Driving SQNet
- ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation ERFNet
- ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation ESPNet
- BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation ECCV2018 code
- A Comparative Study of Real-time Semantic Segmentation for Autonomous Driving
- Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation EDANet
- Light-Weight RefineNet for Real-Time Semantic Segmentation Light-Weight RefineNet
- Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
- CGNet: A Light-weight Context Guided Network for Semantic Segmentation arxiv2018 code
- ShelfNet for Real-time Semantic Segmentation arxiv2018 code
- Concentrated-Comprehensive Convolutions for lightweight semantic segmentation arxiv2018
- ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network cvpr2019 code
- Fast-SCNN: Fast Semantic Segmentation Network arxiv2019 code blog
- An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions arxiv2019
- Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation cvpr2019
- DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation cvpr2019Megvii
- Real time backbone for semantic segmentation arxiv2019
- Residual Pyramid Learning for Single-Shot Semantic Segmentation arxiv2019
- Knowledge Adaptation for Efficient Semantic Segmentation cvpr2019
- In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images cvpr2019 code
- Towards Real-Time Automatic Portrait Matting on Mobile Devices arxiv2019 code
- PortraitNet: Real-time Portrait Segmentation Network for Mobile Device Computers & Graphics 2019 code
- Design of Real-time Semantic Segmentation Decoder for Automated Driving VISAPP2019
- ThunderNet: A Turbo Unified Network for Real-Time Semantic Segmentation WACV2019
- LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation ICIP2019 code
- Accurate Facial Image Parsing at Real-Time Speed TIP2019
- Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images arxiv2019
- Nail Polish Try-On: Realtime Semantic Segmentation of Small Objects forNative and Browser Smartphone AR Applications CVPRW2019
- ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation arxiv2019 code
- Real-time Hair Segmentation and Recoloring on Mobile GPUs 2019CVPRW
- Efficient Segmentation: Learning Downsampling Near Semantic Boundaries arxiv2019
- Multi-Class Lane Semantic Segmentation using Efficient Convolutional Networks MMSP 2019
- A Comparative Study of High-Recall Real-Time Semantic Segmentation Based on Swift Factorized Network SPIE Security + Defence 2019 code
- Context-Integrated and Feature-Refined Network for Lightweight Urban Scene Parsing arxiv2019
- DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation BMVC2019 code
- Learning Lightweight Lane Detection CNNs by Self Attention Distillation ICCV2019 torchRepo
- SqueezeNAS: Fast neural architecture search for faster semantic segmentation arxiv2019 code submitted to ICCV Neural Architects workshop
- ExtremeC3Net: Extreme Lightweight Portrait Segmentation Networks using Advanced C3-modules arxiv2019 ExtremeC3Net Seoul National University && Clova AI, NAVER Corp
- Customizable Architecture Search for Semantic Segmentation cvpr2019 University of Science and Technology of China && JD AI Research
- See More than Once – Kernel-Sharing Atrous Convolution for Semantic Segmentation arxiv2019 University of Technology Sydney && East China Normal University
- Feature Pyramid Encoding Network for Real-time Semantic Segmentation BMVC2019 The University of Manchester
- Graph-guided Architecture Search for Real-time Semantic Segmentation arxiv2019 SenseTime Research && Zhejiang University
- Eye Semantic Segmentation with a Lightweight Model ICCVW 2019 code Chonnam National University
- FDDWNet: A Lightweight Convolutional Neural Network for Real-time Sementic Segmentation arxiv2019 Nanjing University of Posts & Telecommunications
- Real-Time Semantic Segmentation via Multiply Spatial Fusion Network arxiv2019 Beihang University &&Megvii Technology&&Peng Cheng Laboratory
- RGPNet: A Real-Time General Purpose Semantic Segmentation arxiv2019 Advanced Research Lab, NavInfo Europe
- LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation DICTA2019
- FasterSeg: Searching for Faster Real-time Semantic Segmentation ICIR2020 FasterSeg Texas A&M University && Horizon Robotics Inc
- Real-time Segmentation and Facial Skin Tones Grading arxiv2019 HLRNet
- SINet: Extreme Lightweight Portrait Segmentation Networks with Spatial Squeeze Modules and Information Blocking Decoder WACV2020 SINet
- FarSee-Net: Real-Time Semantic Segmentation by Efficient Multi-scale Context Aggregation and Feature Space Super-resolution ICRA2020 SenseTime && Tokyo University
- Cars Can’t Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks CVPR2020 HANet Korea University && CA
- Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes arxiv2020 XMU
- Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation arxiv2020 ZheJiang University
- BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation arxiv2020 BiSeNet V2 bisenetv2-tensorflow HUST && The University of Adelaide &&CUHK && Tencent
- Bi-direction Context Propagation Network for Real-time Semantic Segmentation arxiv2020 Hefei University of Technology
- LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation arxiv2020 SJTU
- Real-time Semantic Segmentation with Fast Attention arxiv2020 Homepage FANet Boston University && Adobe Research
- Ultra Fast Structure-aware Deep Lane Detection ECCV2020 code Zhejiang University
- Improving Semantic Segmentation via Decoupled Body and Edge Supervision ECCV2020 DecoupleSegNets Peking University && University of Oxford && SenseTime Research && Zhejiang Lab
- Semantic Segmentation With Multi Scale Spatial Attention For Self Driving Cars arxiv2020
- EfficientSeg: An Efficient Semantic Segmentation Network arxiv2020 EfficientSeg
- Dense Dual-Path Network for Real-time Semantic Segmentation ACCV2020
- CABiNet: Efficient Context Aggregation Network for Low-Latency Semantic Segmentation arxiv2020
- SegBlocks: Block-Based Dynamic Resolution Networks for Real-Time Segmentation arxiv2020 KU Leuven
- Real-Time High-Resolution Background Matting arxiv2020 hompage BackgroundMattingV2 University of Washington
- Is a Green Screen Really Necessary for Real-Time Portrait Matting? arxiv2020 MODNet City University of Hong Kong, SenseTime Research
- HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation arxiv2020 Facebook AI, Tel Aviv University
- Boundary-Aware Segmentation Network for Mobile and Web Applications submitted to TPAMI BASNet
- EADNet: Efficient Asymmetric Dilated Network for Semantic Segmentation arxiv2021 Fudan University , etc.
- AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing AAAI2021
- Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes arxiv2021
- Rethinking BiSeNet For Real-time Semantic Segmentation CVPR2021 STDC-Seg
- TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation CVPR2022 code
- YOLACT: Real-time Instance Segmentation ICCV2019 code University of California, Davis
- CenterMask:Real-Time Anchor-Free Instance Segmentation VovnetV2 CenterMask CenterMask2 ETRI
- YOLACT++ Better Real-time Instance Segmentation [arxiv2019](YOLACT++ Better Real-time Instance Segmentation) University of California, Davis
- BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation arxiv2020 The University of Adelaide && Southeast University &&Huawei Noah’s Ark Lab
- Deep Snake for Real-Time Instance Segmentation cvpr2020 snake Zhejiang University
- PolarMask: Single Shot Instance Segmentation with Polar Representation cvpr2020 PolarMask HKU
- SOLOv2: Dynamic, Faster and Stronger arxiv2020 SOLOV2 UnofficialPytorchRepo The University of Adelaide && Tongji University && ByteDance AI Lab
- YolactEdge: Real-time Instance Segmentation on the Edge arxiv2020 YolactEdge
- U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection PR2020 U-2-Net
- Highly Efficient Salient Object Detection with 100K Parameters ECCV2020 CSNet
- MobileSal: Extremely Efficient RGB-D Salient Object Detection arxiv2020
- An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection CVPR2019 CEFRL Workshop VOVNetPytorch ETRI
- EfficientDet: Scalable and Efficient Object Detection arxiv2019 unofficial-EfficientDet.Pytorch Google Research, Brain Team
- RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices arxiv2019 Tencent Research&&HKUST
- Learning Spatial Fusion for Single-Shot Object Detection arxiv2019 yolov3+ Beihang University
- CSPNet: A New Backbone that can Enhance Learning Capability of CNN arxiv2019 CSPNet research teams from TaiWan
- YOLOv4: Optimal Speed and Accuracy of Object Detection arxiv2020 OfficialRepo Minimal PyTorch Tensorflow 2.0Repo KerasRepo
- YOLO Nano: a Highly Compact You Only Look Once Convolutional Neural Network for Object Detection arxiv2019
- PC-DARTS: Partial Channel Connections for Memory-Efficient Differentiable Architecture Search arxiv2019 code Shanghai Jiao Tong University&&Huawei
- Densely Connected Search Space for More Flexible Neural Architecture Search arxiv2019 code Huazhong University of Science and Technology &&Horizon Robotics
- FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search arxiv2019 code Xiaomi AI Lab
- XferNAS: Transfer Neural Architecture Search arxiv2019 IBM Research
- AutoML: A Survey of the State-of-the-Art arxiv2019 Hong Kong Baptist University
- MoGA: Searching Beyond MobileNetV3 arxiv2019 code Xiaomi AI Lab
- ScarletNAS: Bridging the Gap Between Scalability and Fairness in Neural Architecture Search arxiv2019 code Xiaomi AI Lab && IoT
- BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search arxiv code blog
- Fast and Practical Neural Architecture Search iccv2019 CUHK && YouTu Lab, Tencent
- Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search arxiv2019 FairDARTS Xiaomi AI Lab &&Minzu University of China
- SGAS: Sequential Greedy Architecture Search arxiv2019 project KAUST && Intel Labs
- Blockwisely Supervised Neural Architecture Search with Knowledge Distillation arxiv2019 DNA DarkMatter AI Research && Monash University &&Sun Yat-sen University
- EDAS: Efficient and Differentiable Architecture Search arxiv2019 KAIST
- Efficient Differentiable Neural Architecture Search with Meta Kernels arxiv2019 HUST &&YITU &&NUS
- AtomNAS: Fine-Grained End-to-End Neural Architecture Search ICIR2020 AutoNAS Johns Hopkins University && ByteDance AI Lab
- EcoNAS: Finding Proxies for Economical Neural Architecture Search arxiv2020 The University of Sydney &&Nanyang Technological University&&SenseTime Research
- MixPath: A Unified Approach for One-shot Neural Architecture Search arxiv2020 MixPath Xiaomi AI Lab &&UCAS
- Efficient Transformers: A Survey arxiv2020
- Escaping the Big Data Paradigm with Compact Transformers arxiv2021 compact- transformer
- EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers arxiv2022
- MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer ICLR2022code
- EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers arxiv2022 code
- SepViT: Separable Vision Transformer arxiv2022
- MoCoViT: Mobile Convolutional Vision Transformer arxiv2022
- Lightweight Vision Transformer with Cross Feature AttentionTechnical Report
- Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios arxiv2022
- Training data-efficient image transformers & distillation through attention arxiv2021 DEIT
- Token Labeling: Training a 85.5% Top-1 Accuracy Vision Transformer with 56M Parameters on ImageNet arxiv2021 TokenLabeling
- Improve Vision Transformers Training by Suppressing Over-smoothing arxiv2021 PatchVisionTransformer
- A Recipe for Training Neural Networks (Apr 25, 2019)
- Improving deep learning models with bag of tricks (Dec 13,2018)
- A Bag of Tricks for Image Classification (Dec 17, 2018)
- Bag of Tricks for Image Classification with Convolutional Neural Networks cvpr2019 code
- Bag of Freebies for Training Object Detection Neural Networks arxiv2019 code
- Bag of Tricks for Image Classification by Arthur Kuzin 2020slide
- carrier-of-tricks-for-classification-pytorch 2020code
- Faster Deep Learning Training with PyTorch – a 2021 Guide
- Awesome-model-compression-and-acceleration
- awesome-model-compression-and-acceleration
- Model-Compression-Papers
- Awesome-model-compression-and-acceleration
- awesome-AutoML-and-Lightweight-Models
- 常用的语义分割架构结构综述以及代码复现
- Efficient-Segmentation-Networks
- Real-time Portrait Segmentation on Smartphones
- Mobile Real-time Video Segmentation
- Real-Time deep learning in mobile application
- QNNPACK: Open source library for optimized mobile deep learning
- 第十七章 模型压缩及移动端部署
- Tips for building fast portrait segmentation network with TensorFlow Lite
-
$\color{red}{*}$ Literature On Neural network architecture - A 2019 Guide to Semantic Segmentation
- Semantic Segmentation
- Image segmentation in 2020: Architectures, Losses, Datasets, and Frameworks
- New mobile neural network architectures
- NanoDet
- Real-Time Video Segmentation on Mobile Devices
- LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation
- mobile_phone_human_matting
- Real-Time Semantic Segmentation in Mobile device
- Semantic Segmentation on PyTorch
- Lightweight-Segmentation
- A PyTorch-Based Framework for Deep Learning in Computer Vision
- A high performance semantic segmentation toolkit based on PaddlePaddle
- PyTorch image models, scripts, pretrained weights
- fast semantic segmentation models on CityScapes/Camvid DataSet by Pytorch
- A semantic segmentation framework by pyotrch
- PyTorch for Semantic Segmentation
- murufeng/awesome_lightweight_networks
- sithu31296/semantic-segmentation
- ncnn
- paddle
- bolt
- Mace
- Mnn