Methods › Computer Vision › Convolutional Neural Networks
Convolutional Neural Networks
Image Models are methods that build representations of images for downstream tasks such as classification and object detection. The most popular subcategory are convolutional neural networks. Below you can find a continuously updated list of image models.
Methods
All 112 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.
| CapsNet Capsule Network | – | 202 |
| 3D CNN 3 Dimensional Convolutional Neural Network | – | 178 |
| CSPDarknet53 | – | 132 |
| ResNeXt | – | 132 |
| GoogLeNet | – | 122 |
| Inception-v3 | – | 98 |
| SqueezeNet | – | 97 |
| VGG-19 Visual Geometry Group 19 Layer CNN | – | 87 |
| HRNet | – | 75 |
| MobileNetV1 | – | 74 |
| PCB Part-based Convolutional Baseline | – | 54 |
| Darknet-19 | – | 52 |
| ShuffleNet | – | 51 |
| SENet | – | 47 |
| VGG-16 | – | 46 |
| LeNet | 1998 | 45 |
| EfficientNetV2 | – | 43 |
| RegNetY | – | 24 |
| GhostNet | – | 22 |
| MnasNet | – | 20 |
| DPN Dual Path Network | – | 19 |
| CheXNet | – | 18 |
| Inception-ResNet-v2 | – | 18 |
| Inception v2 | – | 15 |
| R(2+1)D | – | 14 |
| ShuffleNet v2 | – | 14 |
| Inception-v4 | – | 13 |
| RepVGG | – | 13 |
| ResNeSt | – | 13 |
| FBNet | – | 12 |
| MixNet | – | 12 |
| ResNet-D | – | 10 |
| PyramidNet | – | 9 |
| RevNet | – | 9 |
| AmoebaNet | – | 7 |
| OverFeat | – | 7 |
| ScaleNet | – | 7 |
| CLRNet Convolutional LSTM based Residual Network | – | 6 |
| CR-NET | – | 6 |
| FractalNet | – | 6 |
| SNet | – | 6 |
| SimpleNet | – | 6 |
| ZFNet | – | 6 |
| DetNet | – | 5 |
| Fast-YOLOv2 | – | 5 |
| Single-path NAS | – | 5 |
| SpineNet | – | 5 |
| VoVNet | – | 5 |
| PanNet Pansharpening Network | – | 4 |
| SCARLET | – | 4 |
| SKNet | – | 4 |
| Siamese U-Net | – | 4 |
| CSPResNeXt | – | 3 |
| PeleeNet | – | 3 |
| SqueezeNeXt | – | 3 |
| ACNN block Atrous-convolution block | – | 2 |
| Assemble-ResNet | – | 2 |
| Big-Little Net | – | 2 |
| CDIL-CNN Circular Dilated Convolutional Neural Networks | – | 2 |
| DELG | – | 2 |
| DRPNN Deep Residual Pansharpening Neural Network | – | 2 |
| DenseNet-Elastic | – | 2 |
| ECA-Net | – | 2 |
| Fast-OCR | – | 2 |
| Fast-YOLOv3 | – | 2 |
| Fast-YOLOv4-SmallObj | – | 2 |
| GENet GPU-Efficient Network | – | 2 |
| MCKERNEL | – | 2 |
| MultiGrain | – | 2 |
| PocketNet | – | 2 |
| PolyConv Polynomial Convolution | – | 2 |
| ProxylessNet-Mobile | – | 2 |
| RandWire | – | 2 |
| RegNetX | – | 2 |
| ResNet-RS | – | 2 |
| ABNet ANDHRA Bandersnatch Network | – | 1 |
| ASLFeat | – | 1 |
| AlterNet | – | 1 |
| CDCC-NET | – | 1 |
| CSPDenseNet | – | 1 |
| CSPDenseNet-Elastic | – | 1 |
| CSPPeleeNet | – | 1 |
| ConvMLP | – | 1 |
| CornerNet-Squeeze Hourglass | – | 1 |
| Deep-CAPTCHA | – | 1 |
| DenseNAS-A | – | 1 |
| DenseNAS-B | – | 1 |
| DenseNAS-C | – | 1 |
| DetNASNet | – | 1 |
| DiCENet | – | 1 |
| ESPNetv2 | – | 1 |
| GreedyNAS-A | – | 1 |
| GreedyNAS-B | – | 1 |
| GreedyNAS-C | – | 1 |
| HS-ResNet | – | 1 |
| Harm-Net | – | 1 |
| IkshanaNet The Ikshana Hypothesis of Human Scene Understanding Mechanism | – | 1 |
| MoGA-A | – | 1 |
| MoGA-B | – | 1 |
| MoGA-C | – | 1 |
| MobileNet-V4 | – | 1 |
| PReLU-Net | – | 1 |
| Partial Hybrid Transfer Learning | – | 1 |
| ResNeXt-Elastic | – | 1 |
| SAENet Squeeze aggregated excitation network | – | 1 |
| SPP-Net | – | 1 |
| TResNet | – | 1 |
| VoVNetV2 | – | 1 |
| Z-PNN Pansharpening by convolutional neural networks in the full resolution framework | – | 1 |
| hdxresnet Hybrid-deconvolution | – | 1 |
| uNetXST | – | 1 |
| VGGoptiVMD VGG and variational Model Decomposition | – | 0 |