/ai_papers

AI Papers

Apache License 2.0Apache-2.0

Image Classification

Date Network Paper
1409 VGG Very Deep Convolutional Networks for Large-Scale Image Recognition
1512 ResNet Deep Residual Learning for Image Recognition
1603 ResNetV2 Identity Mappings in Deep Residual Networks
1611 ResNeXt Aggregated Residual Transformations for Deep Neural Networks
1409 InceptionV1 Going Deeper with Convolutions
1502 InceptionV2 Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
1512 InceptionV3 Rethinking the Inception Architecture for Computer Vision
1602 InceptionV4/InceptionResNetV2 Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
1602 InceptionResNetV2 Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
1608 DenseNet Densely Connected Convolutional Networks
1610 Xecption Xception: Deep Learning with Depthwise Separable Convolutions
1704 MobileNet MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
1707 NASNet Learning Transferable Architectures for Scalable Image Recognition
1905 EfficientNet EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Object Detection

Date Network Paper
1311 RCNN Rich feature hierarchies for accurate object detection and semantic segmentation
1504 Fast RCNN Fast R-CNN
1506 Faster RCNN Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
1512 SSD SSD: Single Shot MultiBox Detector
1506 YOLO_V1 You Only Look Once: Unified, Real-Time Object Detection
1612 YOLO_V2 YOLO9000: Better, Faster, Stronger
1804 YOLO_V3 YOLOv3: An Incremental Improvement
1708 RetinaNet Focal Loss for Dense Object Detection
1904 CenterNet Objects as Points
1908 MatrixNet Matrix Nets: A New Deep Architecture for Object Detection

Semantic Segmentation

Date Network Paper
1505 UNet U-Net: Convolutional Networks for Biomedical Image Segmentation
1511 SegNet SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
1605 FCN Fully Convolutional Networks for Semantic Segmentation
1412 DeepLabV1 Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
1606 DeepLabV2 DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
1706 DeepLabV3 Rethinking Atrous Convolution for Semantic Image Segmentation
1802 DeepLabV3+ Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Instance Segmentation

Date Network Paper
1703 MaskRCNN Mask R-CNN

GAN

Date Network Paper
1406 GAN Generative Adversarial Networks
1511 DCGAN Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
1606 InfoGAN InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
1703 CycleGAN Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
1812 StyleGAN A Style-Based Generator Architecture for Generative Adversarial Networks
1609 SRGAN Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
1809 ESRGAN ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks