ML Research Wiki / Benchmarks / Image Classification / Places365

Places365

Image Classification Benchmark

Performance Over Time

📊 Showing 6 results | 📏 Metric: Top 1 Accuracy

Top Performing Models

Rank Model Paper Top 1 Accuracy Date Code
1 OmniVec(ViT) 📚 OmniVec: Learning robust representations with cross modal sharing 63.50 2023-11-07 -
2 MixMIM-L(ViT-L) 📚 MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers 60.30 2022-05-26 📦 sense-x/mixmim
3 µ2Net+ (ViT-L/16) 📚 A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems 59.15 2022-09-15 📦 google-research/google-research
4 MixMIM-B (ViT) 📚 MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers 58.90 2022-05-26 📦 sense-x/mixmim
5 InternImage-H（CNN） 📚 InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions 0.00 2022-11-10 📦 opengvlab/internimage 📦 OpenGVLab/M3I-Pretraining 📦 chenller/mmseg-extension
6 ViC-MAE (ViT-L) 📚 ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders 0.00 2023-03-21 📦 jeffhernandez1995/vic-mae 📦 MindCode-4/code-5

All Papers (6)

sense-x/mixmim
google-research/google-research
sense-x/mixmim
opengvlab/internimage OpenGVLab/M3I-Pretraining chenller/mmseg-extension
jeffhernandez1995/vic-mae MindCode-4/code-5