Computer Vision Models

Backbones

• [x] AlexNet - ImageNet Classification with Deep Convolutional Neural Networks, NeurIPS, 2012
• [x] VGGNets - Very Deep Convolutional Networks for Large-Scale Image Recognition, 2014
• [x] GoogLeNet - Going Deeper with Convolutions, 2014
• [x] Inception-V3 - Rethinking the Inception Architecture for Computer Vision, 2015
• [x] Inception-V4 and Inception-ResNet - Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, AAAI, 2016
• [x] ResNet - Deep Residual Learning for Image Recognition, 2015
• [x] SqueezeNet - SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size, 2016
• [x] ResNeXt - Aggregated Residual Transformations for Deep Neural Networks, CVPR, 2016
• [ ] Res2Net - Res2Net: A New Multi-scale Backbone Architecture, TPAMI, 2019
• [x] ReXNet - Rethinking Channel Dimensions for Efficient Model Design, CVPR, 2020
• [x] Xception - Xception: Deep Learning with Depthwise Separable Convolutions, CVPR, 2016
• [x] DenseNet - Densely Connected Convolutional Networks, CVPR, 2016
• [ ] DLA - Deep Layer Aggregation, CVPR, 2017
• [ ] DPN - Dual Path Networks, NeurIPS, 2017
• [ ] NASNet-A - Learning Transferable Architectures for Scalable Image Recognition, CVPR, 2017
• [ ] PNasNet - Progressive Neural Architecture Search, ECCV, 2017
• [x] MobileNets - MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, 2017
• [x] MobileNetV2 - MobileNetV2: Inverted Residuals and Linear Bottlenecks, CVPR, 2018
• [x] MobileNetV3 - Searching for MobileNetV3, ICCV, 2019
• [x] ShuffleNet - ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices, CVPR, 2017
• [x] ShuffleNetV2 - ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design, ECCV, 2018
• [x] MnasNet - MnasNet: Platform-Aware Neural Architecture Search for Mobile, CVPR, 2018
• [x] GhostNet - GhostNet: More Features from Cheap Operations, CVPR, 2019
• [ ] HRNet - Deep High-Resolution Representation Learning for Visual Recognition, TPAMI, 2019
• [ ] CSPNet - CSPNet: A New Backbone that can Enhance Learning Capability of CNN, CVPR, 2019
• [x] EfficientNet - EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, ICML, 2019
• [x] EfficientNetV2 - EfficientNetV2: Smaller Models and Faster Training, ICML, 2021
• [x] RegNet - Designing Network Design Spaces, CVPR, 2020
• [ ] GPU-EfficientNets - Neural Architecture Design for GPU-Efficient Networks, 2020
• [ ] LambdaNetworks - LambdaNetworks: Modeling Long-Range Interactions Without Attention, ICLR, 2021
• [ ] RepVGG - RepVGG: Making VGG-style ConvNets Great Again, CVPR, 2021
• [ ] HardCoRe-NAS - HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search, ICML, 2021
• [ ] NFNet - High-Performance Large-Scale Image Recognition Without Normalization, ICML, 2021
• [ ] NF-ResNets - Characterizing signal propagation to close the performance gap in unnormalized ResNets, ICLR, 2021
• [x] ConvMixer - Patches are all you need?, 2021
• [x] VGNets - Efficient CNN Architecture Design Guided by Visualization, ICME, 2022
• [x] ConvNeXt - A ConvNet for the 2020s, CVPR, 2022

Attention Blocks

• [x] Non-Local - Non-local Neural Networks, CVPR, 2017
• [x] Squeeze-and-Excitation - Squeeze-and-Excitation Networks, CVPR, 2017
• [x] Gather-Excite - Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks, NeurIPS, 2018
• [x] CBAM - CBAM: Convolutional Block Attention Module, ECCV, 2018
• [x] SelectiveKernel - Selective Kernel Networks, CVPR, 2019
• [x] ECA - ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks, CVPR, 2019
• [x] GlobalContext - GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond, 2019
• [ ] ResNeSt - ResNeSt: Split-Attention Networks, 2020
• [ ] HaloNets - Scaling Local Self-Attention for Parameter Efficient Visual Backbones, 2021

Transformer

• [x] ViT - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, ICLR, 2020
• [ ] DeiT - Training data-efficient image transformers & distillation through attention, ICML, 2020
• [ ] Swin Transformer - Swin Transformer: Hierarchical Vision Transformer using Shifted Windows, ICCV, 2021
• [ ] Twins - Twins: Revisiting the Design of Spatial Attention in Vision Transformers, NeurIPS, 2021

MLP

• [x] MLP-Mixer - MLP-Mixer: An all-MLP Architecture for Vision, NeurIPS, 2021
• [x] ResMLP - ResMLP: Feedforward networks for image classification with data-efficient training, 2021
• [ ] gMLP - Pay Attention to MLPs, 2021

Self-supervised

• [ ] MAE - Masked Autoencoders Are Scalable Vision Learners, CVPR, 2021

Object Detection

• [ ] R-CNN - Rich feature hierarchies for accurate object detection and semantic segmentation, CVPR, 2013
• [ ] Fast R-CNN - Fast R-CNN, ICCV, 2015
• [ ] Faster R-CNN - Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, 2015
• [x] YOLOv1 - You Only Look Once: Unified, Real-Time Object Detection, 2015
• [ ] SSD - SSD: Single Shot MultiBox Detector, ECCV, 2015
• [ ] FPN - Feature Pyramid Networks for Object Detection, 2016

Semantic Segmentation

• [x] FCN - Fully Convolutional Networks for Semantic Segmentation, CVPR, 2014
• [x] UNet - U-Net: Convolutional Networks for Biomedical Image Segmentation, MICCAI, 2015
• [ ] PSPNet - Pyramid Scene Parsing Network, CVPR, 2016
• [x] DeepLabv3 - Rethinking Atrous Convolution for Semantic Image Segmentation, 2017
• [x] DeepLabv3+ - Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation, CVPR, 2018
• [ ] Mask R-CNN - Mask R-CNN, 2017

Generative Models

GANs

• [x] GAN - Generative Adversarial Networks, 2014
• [x] DCGAN - Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, ICLR, 2016
• [ ] WGAN - Wasserstein GAN, 2017

VAEs

• [x] VAE - Auto-Encoding Variational Bayes, 2013
• [x] CVAE - Learning Structured Output Representation using Deep Conditional Generative Models , NeurIPS, 2015
• [ ] β-VAE - beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework, ICLR, 2017

Diffusion Models

Flow-based

Adversarial Attacks

• [x] FGSM - Explaining and Harnessing Adversarial Examples, ICLR, 2014
• [x] PGD - Towards Deep Learning Models Resistant to Adversarial Attacks, ICLR, 2017