This part is mainly to reproduce various models, in order to better understand them

• Vision Transformer

  • ViT:An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
  • Swin Transformer:Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
  • MViTv2:MViTv2: Improved Multiscale Vision Transformers for Classification and Detection

• ResNet:

  • ResNet18, ResNet34, ResNet50, ResNet101, ResNet154:Deep Residual Learning for Image Recognition
  • DenseNet121, DenseNet169, DenseNet201, DenseNet264:Densely connected convolutional networks
  • ResNeXt:Aggregated Residual Transformations for Deep Neural Networks (TODO)

• VGG:

  • VGG16, VGG19:Very deep convolutional networks for large-scale image recognition
  • RepVGG_A0-A2, RepVGG_B0:RepVGG: Making VGG-style ConvNets Great Again

• MobileNet (TODO):

  • MobileNet:Mobilenets: Efficient convolutional neural networks for mobile vision applications
  • EfficientNet:EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
  • EfficientNetV2:EfficientNetV2: Smaller Models and Faster Training
  • TinyNet:Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets

• Text Recognize:

  • CRNN:An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
  • TRBA:What Is Wrong With Scene Text Recognition Model Comparisons?Dataset and Model Analysis
  • SATRN:On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention
  • SRN:Towards Accurate Scene Text Recognition with Semantic Reasoning Networks
  • DPAN:Look Back Again: Dual Parallel Attention Network for Accurate and Robust Scene Text Recognition
  • PARSeq:Scene Text Recognition withPermuted Autoregressive Sequence Models
  • SVTR:SVTR: Scene Text Recognition with a Single Visual Model

• Key Information Extract

  • SDMGR:Spatial Dual-Modality Graph Reasoning for Key Information Extraction (TODO)

• Face Recognition

  • DeepFace:DeepFace: Closing the Gap to Human-Level Performance in Face Verification
  • DeepID:Deep Learning Face Representation from Predicting 10,000 Classes
  • DeepID2:Deep Learning Face Representation by Joint Identification-Verification
  • VarGFaceNet:VarGFaceNet: An Efficient Variable Group Convolutional Neural Network for Lightweight Face Recognition

• RCNN(TODO):
  • R-CNN:Rich feature hierarchies for accurate object detection and semantic segmentation
  • R-FCN:R-FCN: Object Detection via Region-based Fully Convolutional Networks
  • Fast R-CNN:Fast R-CNN
  • Faster R-CNN:Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Yolo:
  • YoloV1:You Only Look Once:Unified, Real-Time Object Detection
  • YoloV2:YOLO9000: Better, Faster, Stronger
  • YoloV3:YOLOv3: An Incremental Improvement
  • YoloV4:YOLOv4: Optimal Speed and Accuracy of Object Detection
  • YoloV5: No Paper, https://github.com/ultralytics/yolov5
  • YoloV7:YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
  • Yolo-Pose:YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss
• Text Detection:
  • EAST:EAST: An Efficient and Accurate Scene Text Detector
  • TextBoxes++:A Single-Shot Oriented Scene Text Detector
• Face Detection:
  • CenterFace:CenterFace: Joint Face Detection and Alignment Using Face as Point
• Detetion Block:
  • SPP:Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
  • FPN:Feature Pyramid Networks for Object Detection

• Text Detection:
  • PSENet:Shape Robust Text Detection With Progressive Scale Expansion Network
  • PANNet:Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
  • DBNet:Real-time Scene Text Detection with Differentiable Binarization
  • DBNet++:Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion
• FCN(TODO)
  • FCN:Fully Convolutional Networks for Semantic Segmentation
  • SegNet:Segnet: A deep convolutional encoder-decoder architecture for image segmentation
  • U-Net:U-Net: Convolutional Networks for Biomedical Image Segmentation
• Tamper Detection:
  • DTD(https://openaccess.thecvf.com/content/CVPR2023/papers/Qu_Towards_Robust_Tampered_Text_Detection_in_Document_Image_New_Dataset_CVPR_2023_paper.pdf)

• Object Detection
  • Bottleneck-LSTM:Mobile Video Object Detection with Temporally-Aware Feature Maps
• Action Recognition
  • DeepVideo:Large-scale Video Classification with Convolutional Neural Networks
  • TDD:Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
  • TSN:Temporal Segment Networks: Towards Good Practices for Deep Action Recognition