Home News Latest Papers Tutorials Datasets Wiki SOTA LLM Models GPU Leaderboard Events

English

Image Classification On Places205

Metrics

Top 1 Accuracy

Results

Performance results of various models on this benchmark

Model Name	Top 1 Accuracy	Paper Title	Repository
MixMIM-L	69.3	MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers
SEER	66.0	Self-supervised Pretraining of Visual Features in the Wild
AutoMix (ResNet-50 Supervised)	64.1	AutoMix: Unveiling the Power of Mixup for Stronger Classifiers
MAE (ViT-H, 448)	66.8	Masked Autoencoders Are Scalable Vision Learners
InternImage-H	71.7%	InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
SwAV	56.7%	Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
SAMix (ResNet-50 Supervised)	64.3	Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
MixMIM-B	68.3	MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers
ResNet-50 (Supervised)	53.2%	Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Barlow Twins (ResNet-50)	54.1%	Barlow Twins: Self-Supervised Learning via Redundancy Reduction
MoCo v2	52.9	Improved Baselines with Momentum Contrastive Learning
SEER (RegNet10B - finetuned - 384px)	69.0	Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision
BYOL	54.0	Bootstrap your own latent: A new approach to self-supervised Learning
RegNetY-128GF (Supervised)	62.7	Self-supervised Pretraining of Visual Features in the Wild
SimCLR	53.3	A Simple Framework for Contrastive Learning of Visual Representations

0 of 15 row(s) selected.