New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Vision AI models
Browse the complete list of Vision AI models. Compare specifications, benchmark scores and provider pricing on GenAIList.
Image-to-image cGAN
🇺🇸 University of California (UC) Berkeley
PolyNet
🇺🇸 Chinese University of Hong Kong (CUHK)
ResNeXt-101 (64×4d)
🇺🇸 University of California San Diego
ResNeXt-50
🇺🇸 University of California San Diego
Deeply-recursive ConvNet
🇺🇸 Seoul National University
DTN (Domain Transfer Network)
🇺🇸 Facebook AI Research
DLDL (PASCAL)
🇺🇸 University of Oxford
NASv3 (CIFAR-10)
🇺🇸 Google Brain
GAWWN
🇺🇸 University of Michigan
Xception
MS-CNN
🇺🇸 IBM
ResNet-200
🇺🇸 Microsoft Research Asia
Stacked hourglass network
🇺🇸 University of Michigan
Attend-Infer-Repeat
🇺🇸 Google DeepMind
Order embeddings with layer norm
🇺🇸 University of Toronto
PixelCNN
🇺🇸 Google DeepMind
LRR-4X
🇺🇸 UC Irvine
Symmetric Residual Encoder-Decoder Net
🇺🇸 Nanjing University
Binarized Neural Network (MNIST)
🇺🇸 Technion - Israel Institute of Technology
Template Adaptation
🇺🇸 University of Oxford
Order-Embeddings of Images and Language
🇺🇸 University of Toronto
Convolutional Pose Machines
🇺🇸 Carnegie Mellon University (CMU)
ResNet-101 (ImageNet)
🇺🇸 Microsoft
ResNet-152 (ImageNet)
🇺🇸 Microsoft
Inception v3
Multi-scale Dilated CNN
🇺🇸 Princeton University
DCNN
🇺🇸 University of Maryland
CompACT-Deep
🇺🇸 University of California San Diego
BatchNorm
Faster R-CNN
🇺🇸 Microsoft Research
Fast R-CNN
🇺🇸 Microsoft Research
CRF-RNN
🇺🇸 University of Oxford
MSRA (C, PReLU)
🇺🇸 Microsoft Research
VGG-Face
🇺🇸 University of Oxford
ADAM (CIFAR-10)
🇺🇸 University of Amsterdam
DeepLab
Fractional Max-Pooling
🇺🇸 University of Warwick
TA-CNN
🇺🇸 Chinese University of Hong Kong (CUHK)
Cascaded LNet-ANet
🇺🇸 Chinese University of Hong Kong (CUHK)
Fully Convolutional Networks
🇺🇸 University of California (UC) Berkeley
Spatially-Sparse CNN
🇺🇸 University of Warwick
GoogLeNet / InceptionV1
VGG16
🇺🇸 University of Oxford
VGG19
🇺🇸 University of Oxford
DeepFace
🇺🇸 Tel Aviv University
Fragment embedding
🇺🇸 Stanford University
SPPNet
🇺🇸 Microsoft
Dropout: SVHN
🇺🇸 University of Toronto
OverFeat
🇺🇸 New York University (NYU)
Image generation
🇺🇸 University of Amsterdam
DeViSE
Visualizing CNNs
🇺🇸 New York University (NYU)
Hierarchical Scene Labeling (Stanford Background)
🇺🇸 New York University (NYU)
Maxout Networks
🇺🇸 University of Montreal / Université de Montréal
Textual Imager
🇺🇸 Stanford University
DistBelief Vision
AlexNet
🇺🇸 University of Toronto
Unsupervised High-level Feature Learner
Dropout (CIFAR)
🇺🇸 University of Toronto
Dropout (ImageNet)
🇺🇸 University of Toronto
About Vision AI models
This page lists every Vision AI models tracked on GenAIList. When choosing a model, weigh raw capability against practical constraints like context window, latency, licensing and price. Open-weights and open-source models can be self-hosted and fine-tuned, while proprietary models often lead on raw quality. Compare benchmark scores on our benchmarks page and put two candidates head to head with compare.
Frequently asked questions
How do I choose the right model?
Weigh raw capability against practical constraints like context window, latency, licensing and price. Use the benchmarks page to compare rankings and the compare tool to evaluate two candidates side by side.
Where can I see benchmark scores?
Visit the benchmarks page to compare these models on standardised tests, then use the compare tool for a detailed side-by-side of any two models.