awesome-cv-model
awesome cv model
https://github.com/isLinXu/awesome-cv-model
Last synced: 6 days ago
JSON representation
-
四、PaddleX List
-
五、附录
-
二、影响力数据
-
1、图像分类
- Densely Connected Convolutional Networks
- Repvgg: Making vgg-style convnets great again
- Squeeze-and-Excitation Networks
- Deep Residual Learning for Image Recognition
- MobileNetV2: Inverted Residuals and Linear Bottlenecks
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Rethinking Model Scaling for Convolutional Neural Networks
- Rethinking the Inception Architecture for Computer Vision
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Shufflenet v2: Practical guidelines for efficient cnn architecture design
-
2、目标检测
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- SSD: Single Shot MultiBox Detector
- Focal Loss for Dense Object Detection
- Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection
- Cascade R-CNN: High Quality Object Detection and Instance Segmentation
- End-to-End Object Detection with Transformers
- FCOS: Fully Convolutional One-Stage Object Detection
- YOLOv3: An Incremental Improvement
- Objects as Points
-
5、动作识别
-
4、语义分割
- Unified Perceptual Parsing for Scene Understanding
- U-Net: Convolutional Networks for Biomedical Image Segmentation
- Fully Convolutional Networks for Semantic Segmentation
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Pyramid Scene Parsing Network
-
7、OCR
-
3、实例分割
-
6、2D姿态估计
-
Categories