- LeNet
- AlexNet
- VGG
- Inception
- Inception-v2/v3
- Inception-v4
- ResNet
- DenseNet
- ResNeXt
- ResNet-SB
- MobileNet
- MobileNetv2
- MobileNetv3
- SPPNet
- ShuffleNet
- NAS-Net
- EfficientNet
- SeNet
- ConvNeXt
-
- Vision Transformers
- DeiT
- DeiT-III
- Tokens to Tokens ViT
- Bottleneck Transformers
- Transformer in Transformer
- Hierarchical Pooling ViT
- Convolutional Inductive ViT
- Deeper ViT
- Convolution Designs in ViT
- Swin-Transformers
- Cross Attention ViT
- Rethinking Spatial Dimensions of ViT
- Convolutions to ViT
- Going Deeper with ViT
- Compact Convolutional Transformer
- Locality ViT
- VisFormer
- Spatial Attention in Transformers
- MLP-Mixer
- ViT SAM
- Dynamic ViT
- Refiner ViT
- Scaling ViT
- Cross CoVariance ViT
- Dino
- Dinov2
- Faster R-CNN
- Cascade R-CNN
- YOLO
- YOLOv3
- SSD
- FPN
- RetinaNet
- CornerNet
- EfficientDet
- CenterNet
- Grid R-CNN
- Repulsion Loss
- Deformable ConvNets
- FSAF for Single Shot
- FCNet
- U-Net
- SegNet
- DilatedNet
- DeepLab
- E-Net
- LRR
- PixelNet
- RefineNet
- PSPNet
- GCN
- Mask R-CNN
- LinkNet
- DeepLabv3
- SegAware
- FRRN
- ERFNet
- PixelDCN
- ShuffleSeg
- MultiNet
- R2U-Net
- HDC-DUC
- ERFNet-DG
- UNet++
- BiSeNet
- ICNet
- OCNet
- DeepLabv3+
- DenseASPP
- Fast-SCNN
- FastFCN
- DFANet
- DUNet
- LEDNet
- HRNet
- LadderNet
- ShelfNet
- BiSeNet-v2