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.
YOLOX-X
🇨🇳 Megvii Inc
SEER
🇺🇸 Facebook AI Research
EfficientNetV2-XL
Denoising Diffusion Probabilistic Models (LSUN Bedroom)
🇺🇸 University of California (UC) Berkeley
CoAtNet
ViT-G/14
🇺🇸 Google Brain
Transformer local-attention (NesT-B)
🇺🇸 Google Cloud
ViT + DINO
🇺🇸 INRIA
ResNet-RS
🇺🇸 Google Brain
Meta Pseudo Labels
🇺🇸 Google Brain
DeiT-B
🇺🇸 Meta AI
HiPPO-LegS
🇺🇸 Stanford University
ViT-Huge/14
🇺🇸 Google Brain
iGPT-XL
🇺🇸 OpenAI
DETR
Once for All
🇺🇸 MIT-IBM Watson AI Lab
Cube-Space AutoEncoder
🇺🇸 MIT-IBM Watson AI Lab
Big Transfer (BiT-M)
🇺🇸 Google Brain
StarGAN v2
🇰🇷 NAVER
Noisy Student (L2)
🇺🇸 Carnegie Mellon University (CMU)
Self-Attention and Convolutional Layers
🇨🇭 Ecole Polytechnique F´ed´erale de Lausanne (EPFL)
AlphaX-1
🇺🇸 Facebook AI Research
ResNet-152 + ObjectNet
🇺🇸 Massachusetts Institute of Technology (MIT)
Graph-based Semi-Supervised Learning (GSSL) Model on MNIST
🇺🇸 West Virginia University
LaNet-L (CIFAR-10)
🇺🇸 Brown University
MnasNet-A1 + SSDLite
MnasNet-A3
EfficientNet-B1
Neuro-Symbolic Concept Learner
🇺🇸 Massachusetts Institute of Technology (MIT)
DANet
🇨🇳 Chinese Academy of Sciences
ProxylessNAS
🇺🇸 Massachusetts Institute of Technology (MIT)
Decoupled weight decay regularization
🇩🇪 University of Freiburg
Vine copula (breast cancer)
🇺🇸 Massachusetts Institute of Technology (MIT)
ESRGAN
🇺🇸 Chinese University of Hong Kong (CUHK)
Big-Little Net
🇺🇸 IBM
Big-Little Net (vision)
🇺🇸 IBM
ResNeXt-101 32x48d
Diffractive Deep Neural Network
🇺🇸 University of California Los Angeles (UCLA)
YOLOv3
🇺🇸 University of Washington
Residual Dense Network
🇺🇸 Northeastern University
TCN (P-MNIST)
🇺🇸 Carnegie Mellon University (CMU)
DeepLabV3+
AmoebaNet-A (F=448)
🇺🇸 Google Brain
DenseNet201
🇨🇳 Tsinghua University
Refined Part Pooling
🇨🇳 Tsinghua University
PNASNet-5
🇺🇸 Johns Hopkins University
DL scaling Image
🇨🇳 Baidu
VQ-VAE
🇬🇧 DeepMind
ProgressiveGAN
🇺🇸 NVIDIA
LRSO-GAN
🇨🇳 University of Technology Sydney
PyramidNet
🇰🇷 Korea Advanced Institute of Science and Technology (KAIST)
Adversarial Joint Adaptation Network (ResNet)
🇨🇳 Tsinghua University
Cutout-regularized net
🇨🇦 University of Guelph
RetinaNet-R101
🇺🇸 Facebook AI Research
PSPNet
🇺🇸 Chinese University of Hong Kong (CUHK)
JFT
🇺🇸 Google Research
DeepLabV3
EDSR
🇺🇸 Seoul National University
SRGAN
Low-Cost Collaborative Network
🇨🇳 National University of Singapore
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.