HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Self Supervised Image Classification On

Metrics

Number of Params
Top 1 Accuracy

Results

Performance results of various models on this benchmark

Model Name
Number of Params
Top 1 Accuracy
Paper TitleRepository
DINOv2 distilled (ViT-S/14)21M81.1%DINOv2: Learning Robust Visual Features without Supervision
SwAV (ResNet-50 x2)94M77.3%Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
MoCo (ResNet-50 4x)375M68.6%Momentum Contrast for Unsupervised Visual Representation Learning
EsViT(Swin-S)49M80.8Efficient Self-supervised Vision Transformers for Representation Learning
AMDIM (arxiv v1)337M60.2%Learning Representations by Maximizing Mutual Information Across Views
SwAV (ResNet-50)24M75.3%Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
CaCo (ResNet-50)24M75.7%CaCo: Both Positive and Negative Samples are Directly Learnable via Cooperative-adversarial Contrastive Learning
iGPT-XL (64x64, 3072 features)6800M68.7%Generative Pretraining from Pixels
LocalAgg (ResNet-50)24M60.2%Local Aggregation for Unsupervised Learning of Visual Embeddings
MAE-CT (ViT-H/16)632M82.2%Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget
iGPT-L (48x48)1400M65.2%Generative Pretraining from Pixels
EsViT (Swin-B)87M81.3Efficient Self-supervised Vision Transformers for Representation Learning
PercMAE (ViT-B)80M78.1%Improving Visual Representation Learning through Perceptual Understanding
MAE (ViT-B)80M68.0%Masked Autoencoders Are Scalable Vision Learners
DINOv2 distilled (ViT-B/14)85M84.5%DINOv2: Learning Robust Visual Features without Supervision
SimCLRv2 (ResNet-50 x2)94M75.6%Big Self-Supervised Models are Strong Semi-Supervised Learners
MIM-Refiner (MAE-ViT-2B/14)1890M84.5%MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
MV-MR-74.5%MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
MAE (ViT-L)306M75.8%Masked Autoencoders Are Scalable Vision Learners
ReLICv2 (ResNet101)44M78.7%Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
0 of 142 row(s) selected.