Hello Computervision!

This repository is papers that contribute the computer vision that i read.

Contents

• Image Classification
• Segmentation
• Generative Model
• Object detection
• Self-supervised learning
• NLP(National Language Processing)

---

Image Classification

• Lenet(Gradient Based Learning Applied to Document Recognition, 1998) Code , Paper Link, Paper Review

• AlexNet(ImageNet Classfication with Deep Convolutional Neural Networks, 2012) Code, Paper Link, Paper Review

• VGGNet(Very Deep Convolutional Networks for Large Scale Image Resoultion, 2015) Code, Paper Link, Paper Review

• SPPNet(Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, 2014) Code, Paper Link, Paper Review

• GoogleNet(Going deeper with convolutions, 2015) Code, Paper Link, Paper Review

• ResNet(Deep residual Learning for Image Recognition, 2016) Code, Paper Link, Paper Review

• SqueezeNet(Alexnet-Level accuracy with 50x fewer parameters and 0.5MB model size, 2017) Code, Paper Link, Paper Review

• DenseNet(Densely Connected Convolutional Networks, 2017) Code, Paper Link, Paper Review

• XceptionNet(Xception: Deep Learnning with depthwise separable convolutions, 2017) Code, Paper Link, Paper Review

• MobileNetV1(MobileNets: Efficient Convolutional Neural networks for mobile vision application, 2017) Code, Paper Link, Paper Review

• ShuffleNet(ShuffleNet: An extremlely efficient convolutional neural networks for mobile devices, 2017) Code, Paper Link, Paper Review

• ResNext(Aggregated Residual Transormations for Deep Neural Networks, 2017) Code, Paper Link, Paper Review

• MobileNetV2(MobileNetV2: Inverted residual and linear bottlenecks, 2018) Code, Paper Link, Paper Review

• Squeeze Excitation Network(Squeeze and Excitation Network, 2018) Code, Paper Link, Paper Review

• Residual Attention Network(Residual Attention Network for image classification, 2017) Code, Paper Link, Paper Review

• BAM(BottleNeck Attention Module, 2018) Code, Paper Link, Paper Review

• CBAM(CBAM: Convolutional Block Attention Module, 2018) Code, Paper Link, Paper Review

• EfficientNet(EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, 2019) Code, Paper Link, Paper Review

• Vision Transformer(An Image is worth 16x16 words: Transformers for image recognition at scale, 2020) Code, Paper Link, Paper Review

• Swin Transformer(Swin Transformer, Hierarchical Vision Transformer using Shifted Windows, 2021) Code, Paper Link, Paper Review

• Hybrid Swin Transformer(Hybrid Swin Transformer: Efficient large-scale image retrieval with deep feature orthogonality and Hybrid-Swin-Transformers, 2021) Code, Paper Link, Paper Review

• ConvNext(A ConvNet for the 2020s, 2022) Code, Paper Link, Paper Review

• ConvNextV2(ConvNextV2: Co-designing and Scaling ConvNets with Masked Autoencoders, 2022) Code, Paper Link, Paper Review

Object Detection

• R-CNN(Rich feature hierarchies for accurate object detection and semantic segmentation, 2014) Code, Paper Link, Paper Review

• Fast R-CNN(Fast R-CNN, 2015) Code, Paper Link, Paper Review

• Faster R-CNN(Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, 2015) Code, Paper Link, Paper Review

• YOLO V1(You Only Look Once: Unified, Real-Time Object Detection, 2016) Code, Paper Link, Paper Review

• SSD(SSD: Single Shot MultiBox Detector, 2016) Code, Paper Link, Paper Review

• FPN(Feature Pyramid Networks for Object Detection, 2016) Code, Paper Link, Paper Review

Segmentation

• Deeplab v1(Semantic image segmentation with deep convolutional nets and fully connected CRFs, 2014) Code, Paper Link, Paper Review

• FCN(Fully Convolutional Networks for Semantic Segmentation, 2014) Code, Paper Link, Paper Review

• SegNet(SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation, 2015) Code, Paper Link, Paper Review

• Segformer(SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers, 2021) Code, Paper Link, Paper Review

Generative Model

• GAN(Generative Adversarial Network, 2014) : Code , Paper Link, Paper Review

• DCGAN(Deep Convolutional Generative Adversarial Network, 2016) : Code , Paper Link, Paper Review

• cGAN(Conditional Generative Adversarial Network, 2014) : Code , Paper Link, Paper Review

• LSGAN(Least Square Generative Adversarial Network, 2017) : Code , Paper Link, Paper Review

• InfoGAN(Information Maximizing Generative Adversarial Network, 2016) : Code , Paper Link, Paper Review

• WGAN(Wasserstein GAN, 2017) : Code , Paper Link, Paper Review

• CycleGAN(Cycle Consistent GAN, 2017): Code , Paper Link, Paper Review

• U-Net(U-Net, 2015): Code , Paper Link, Paper Review

• Pix2Pix(Image to Image Translation with Conditional Adversarial Networks, 2016) : Code , Paper Link, Paper Review

• AutoEncoder(2011) : Code

• StyleTransfer(2015) : Code , Paper Link Paper Review

• AdaIN Style Transfer(Adaptive Instance Normalization, 2017) : Code , Parper Link

• VAE(AutoEncoding Variational Bayes, 2014) : Code , Parper Link

NLP

• Attention(Neural Machine Translation By Jointly Learning to Align and translate, 2015) : Code , Paper Link, Paper Review

Self-supervised learning

• SimCLR(A Simple Framework for contrastive learning of visual representation, 2020) : Code , Paper Link, Paper Review

• MocoV1(Momentum contrast for unsupervised visual representation learning, 2020) : Code , Paper Link, Paper Review

• BYOL(2020) : Code , Paper Link , Paper Review

• SwAV(2020) : Code , Paper Link , Paper Review

• SimSiam(Exploring Simple siamese representation learning, 2020) : Code , Paper Link , Paper Review

• DINO(Emerging properties in self-supervised vision transformers, 2021) : Code , Paper Link , Paper Review

• MAE(Masked Autoencoder are scalable vision learners, 2021) : Code , Paper Link , Paper Review

• PAWS(Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples, 2021) : Code , Paper Link , Paper Review

• BEiT(BERT Pre-Training of Image Transformers, 2021) : Code , Paper Link , Paper Review

• SimMIM(SimMIM: a Simple Framework for Masked Image Modeling, 2021) : Code , Paper Link , Paper Review