논문 읽어온 것들 간단히 정리
| Num | Name | Paper Name |
|---|---|---|
| 01 | U-Net | U-Net : Convolutional Networks for Biomedical Image Segmentation |
| https://github.com/sooah/Paper_Study/blob/master/Segmentation/U-Net_Convolutional_Networks_for_Biomedical_Image_Segmentation.pdf | ||
| 02 | FCN | Fully Convolutional Networks for Semantic Segmentation |
| 03 | Learning Deconvolutional Network for Semantic Segmentation | |
| 04 | SegNet | SegNet : A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation |
| 05 | DeepLab V1 | Semantic ImageSegmentation with Deep Convolutional Nets and Fully Connected CRFs |
| 06 | DeepLab V2 | DeepLab : Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution and Fully Connected CRFs |
| 07 | YOLO | You Only Look Once |
| 08 | Attention U-Net | Attention U-Net : Learning Where to Look for the Pancreas |
| 09 | RA-UNet | RA-U Net : 3D hybrid residual attention-aware segmentation |
| https://github.com/sooah/Paper_Study/blob/master/Segmentation/RA-UNet_A_hybrid_deep_attention-aware_network_to_extract_liver_and_tumor_in_CT_scans.md | ||
| 10 | R2U-Net | Recurrent Residual Convolutional Neural Network based on U-Net(R2U-Net) for Medical Image Segmentation |
| https://github.com/sooah/Paper_Study/blob/master/Segmentation/%5BR2U-Net%5DRecurrent_Residual_Convolutional_Neural_Network_based_on_U-Net(R2U-Net)_for_Medical_Image_Segmentation.md | ||
| 11 | DeepLab V3+ | Encoder-decoder with Astrous Separable Convolution for Semantic Image Segmentation |
| https://github.com/sooah/Paper_Study/blob/master/Segmentation/%5BDeepLabV3%2B%5DEncoder-Decoder_with_Atrous_Separable_Convolution_for_Semantic_Image_Segmentation.md |
| Num | Name | Paper Name |
|---|---|---|
| 01 | LeNet-5 | Gradient-Based Learning Applied to Document Recognition |
| 02 | AlexNet | ImageNet Classification with Deep Convolutional Neural Networks |
| 03 | VGG-16 | Very Deep Convolutional Networks for Large-Scale Image Recognition |
| 04 | ResNet | Deep Residual Learning for Image Recognition |
| 05 | Identity Mapping in Deep Residual Networks | |
| 06 | Wide Residual Networks | |
| 07 | DenseNet | Densely Connected Convolutional Networks |
| 08 | InceptionNet | Inception-v3 |
| 09 | Residual Attention Network for Image Classification |
| Num | Name | Paper Name |
|---|---|---|
| 01 | YOLO | You Only Look Once |
| 02 | RCNN | Rich feature hierarchies for accuarate object detection and semantic segmentation |
| [https://github.com/sooah/Paper_Study/blob/master/Object%20Detection/%5BRCNN%5DRich_Feature_Hierarchies_for_Accurate_Object_Detection_and_Semantic_Segmentation.md](https://github.com/sooah/Paper_Study/blob/master/Object Detection/[RCNN]Rich_Feature_Hierarchies_for_Accurate_Object_Detection_and_Semantic_Segmentation.md) | ||
| 03 | Fast RCNN | Fast R-CNN |
| 04 | Faster R-CNN | Faster R-CNN : Towards Real-Time Object Detection with Region Proposal Networks |
| 05 | Mask R-CNN | Mask R-CNN |
| 06 | SSD | SSD : Single Shot Multibox Detector |
| Num | Name | Paper Name |
|---|---|---|
| 01 | Seq2Seq | Sequence to Sequence Learning with Neural Networks |
| 02 | Neural Machine Translation by Jointly Learning to Align and Translation | |
| 03 | Attention | Attention in all you need |
| Num | Name | Paper Name |
|---|---|---|
| 01 | Show, Attend and Tell : Neural Image Caption Generation with Visual Attention |
| Num | Name | Paper Name |
|---|---|---|
| 01 | VAE | Auto-Encoding Variational Bayes |
| Num | Name | Paper Name |
|---|---|---|
| 01 | GAN | Generative Adversarial Nets |
| 02 | DCGAN | Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks |
| 03 | CycleGAN | Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks |
| https://github.com/sooah/Paper_Study/blob/master/GAN/Unpaired_Image-to-Image_Translation_using_Cycle-Consistent_Adversarial_Networks.md | ||
| 04 | StarGAN | StarGAN : Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation |
| https://github.com/sooah/Paper_Study/blob/master/GAN/StarGAN_Unified_Generative_Adversarial_Networks_for_Multi-Domain_Image-to-Image_Translation.md | ||
| 05 | DiscoGAN | Learning to Discover Cross-Domain Relations with Generative Adversarial Networks |
| Num | Name | Paper Name |
|---|---|---|
| 01 | GOTURN | Learning to Track at 100 FPS with Deep Regression Networks |
| 02 | High Performance Visual Tracking with Siamese Region Proposal Network |
| Num | Name | Paper Name |
|---|---|---|
| 01 | Image Denoising and Inpainting with Deep Neural Networks | |
| 02 | Context Encoders : Feature Learning by Inpainting | |
| https://github.com/sooah/Paper_Study/blob/master/Inpainting/Context_Encoders_Feature_Learning_by_Inpainting.pdf |
| Num | Note | Paper Name |
|---|---|---|
| 01 | convolution을 self-attention으로 대체 | Stand-Alone Self-Attention in Vision Models |
| https://github.com/sooah/Paper_Study/blob/master/Stand-Alone_Self-Attention_in_Vision_Models.md |
| Num | Paper Name |
|---|---|
| 01 | Factorization Machines |
| Num | Paper Name |
|---|---|
| 01 | Computed tomography super-resolution using deep convolutional neural network |
| https://github.com/sooah/Paper_Study/blob/master/FMISL/Computed_tomography_super-resolution_using_deep_convolutional_neural_network.pdf | |
| 02 | Measurement of Glomerular Filtration Rate using Quantitative SPECT-CT and Deep-Learning based Kidney Segmentation |
| https://github.com/sooah/Paper_Study/blob/master/FMISL/Measurement_of_Glomerular_Filtration_Rate_using_Quantitative_SPECT-CT_and_Deep-Learning_based_Kidney_Segmentation.pdf |
| Num | Name |
|---|---|
| 01 | Bayes Theorem 과 Sigmoid Softmax 사이 관계 |
| https://github.com/sooah/Paper_Study/blob/master/Relationship_between_Bayes_Theorem_and_Sigmoid_Softmax.pdf |